From 55147744905548a40e6eed0d9755505e0c043c6e Mon Sep 17 00:00:00 2001 From: Ola Hungerford Date: Thu, 17 Apr 2025 19:52:45 -0700 Subject: [PATCH 01/28] Update fetch Readme JSON snippets for installation to be complete JSON --- src/fetch/README.md | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/src/fetch/README.md b/src/fetch/README.md index 01d99cac..1d2f872b 100644 --- a/src/fetch/README.md +++ b/src/fetch/README.md @@ -52,10 +52,12 @@ Add to your Claude settings: Using uvx ```json -"mcpServers": { - "fetch": { - "command": "uvx", - "args": ["mcp-server-fetch"] +{ + "mcpServers": { + "fetch": { + "command": "uvx", + "args": ["mcp-server-fetch"] + } } } ``` @@ -65,10 +67,12 @@ Add to your Claude settings: Using docker ```json -"mcpServers": { - "fetch": { - "command": "docker", - "args": ["run", "-i", "--rm", "mcp/fetch"] +{ + "mcpServers": { + "fetch": { + "command": "docker", + "args": ["run", "-i", "--rm", "mcp/fetch"] + } } } ``` @@ -78,10 +82,12 @@ Add to your Claude settings: Using pip installation ```json -"mcpServers": { - "fetch": { - "command": "python", - "args": ["-m", "mcp_server_fetch"] +{ + "mcpServers": { + "fetch": { + "command": "python", + "args": ["-m", "mcp_server_fetch"] + } } } ``` From 67d71ba3390710c9217d28397d1db2cfa86f7314 Mon Sep 17 00:00:00 2001 From: nolleh Date: Sat, 10 May 2025 23:59:21 +0900 Subject: [PATCH 02/28] docs: added mcp-vertica --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 8bdc5228..26f750aa 100644 --- a/README.md +++ b/README.md @@ -440,6 +440,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Unity3d Game Engine](https://github.com/CoderGamester/mcp-unity)** - An MCP server that enables LLMs to interact with Unity3d Game Engine, supporting access to a variety of the Unit's Editor engine tools (e.g. Console Logs, Test Runner logs, Editor functions, hierarchy state, etc) and executing them as MCP tools or gather them as resources. - **[Unity Integration (Advanced)](https://github.com/quazaai/UnityMCPIntegration)** - Advanced Unity3d Game Engine MCP which supports ,Execution of Any Editor Related Code Directly Inside of Unity, Fetch Logs, Get Editor State and Allow File Access of the Project making it much more useful in Script Editing or asset creation. - **[Vega-Lite](https://github.com/isaacwasserman/mcp-vegalite-server)** - Generate visualizations from fetched data using the VegaLite format and renderer. +- **[Vertica](https://github.com/nolleh/mcp-vertica)** - Vertica database integration in Python with configurable access controls and schema inspection - **[Video Editor](https://github.com/burningion/video-editing-mcp)** - A Model Context Protocol Server to add, edit, and search videos with [Video Jungle](https://www.video-jungle.com/). - **[Virtual location (Google Street View,etc.)](https://github.com/mfukushim/map-traveler-mcp)** - Integrates Google Map, Google Street View, PixAI, Stability.ai, ComfyUI API and Bluesky to provide a virtual location simulation in LLM (written in Effect.ts) - **[VolcEngine TOS](https://github.com/dinghuazhou/sample-mcp-server-tos)** - A sample MCP server for VolcEngine TOS that flexibly get objects from TOS. From 9ef8018779e414330a19e72f6718918d06152ee7 Mon Sep 17 00:00:00 2001 From: Paul-Louis NECH <1821404+PLNech@users.noreply.github.com> Date: Wed, 14 May 2025 15:03:55 +0200 Subject: [PATCH 03/28] feat(README): Add Algolia Official MCP --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 47acea58..d5e5e608 100644 --- a/README.md +++ b/README.md @@ -44,6 +44,7 @@ Official integrations are maintained by companies building production ready MCP - AgentQL Logo **[AgentQL](https://github.com/tinyfish-io/agentql-mcp)** - Enable AI agents to get structured data from unstructured web with [AgentQL](https://www.agentql.com/). - AgentRPC Logo **[AgentRPC](https://github.com/agentrpc/agentrpc)** - Connect to any function, any language, across network boundaries using [AgentRPC](https://www.agentrpc.com/). - Aiven Logo **[Aiven](https://github.com/Aiven-Open/mcp-aiven)** - Navigate your [Aiven projects](https://go.aiven.io/mcp-server) and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services +- Algolia Logo **[Algolia MCP](https://github.com/algolia/mcp-node)** - Connect to a [AnalyticDB for MySQL](https://www.alibabacloud.com/en/product/analyticdb-for-mysql) Algolia MCP Server exposes a natural language interface to query, inspect, and manage Algolia indices and configs. Useful for monitoring, debugging and optimizing search performance within your agentic workflows. See [demo](https://www.youtube.com/watch?v=UgCOLcDI9Lg). - Alibaba Cloud AnalyticDB for MySQL Logo **[Alibaba Cloud AnalyticDB for MySQL](https://github.com/aliyun/alibabacloud-adb-mysql-mcp-server)** - Connect to a [AnalyticDB for MySQL](https://www.alibabacloud.com/en/product/analyticdb-for-mysql) cluster for getting database or table metadata, querying and analyzing data.It will be supported to add the openapi for cluster operation in the future. - Apache IoTDB Logo **[Apache IoTDB](https://github.com/apache/iotdb-mcp-server)** - MCP Server for [Apache IoTDB](https://github.com/apache/iotdb) database and its tools - Apify Logo **[Apify](https://github.com/apify/actors-mcp-server)** - [Actors MCP Server](https://apify.com/apify/actors-mcp-server): Use 3,000+ pre-built cloud tools to extract data from websites, e-commerce, social media, search engines, maps, and more From 29380d99b748b4d2fd3151af8f23a0f00bb93f6d Mon Sep 17 00:00:00 2001 From: Paul-Louis NECH <1821404+PLNech@users.noreply.github.com> Date: Wed, 14 May 2025 18:30:06 +0200 Subject: [PATCH 04/28] chore(README): Fix newline --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index d5e5e608..9b677198 100644 --- a/README.md +++ b/README.md @@ -44,7 +44,7 @@ Official integrations are maintained by companies building production ready MCP - AgentQL Logo **[AgentQL](https://github.com/tinyfish-io/agentql-mcp)** - Enable AI agents to get structured data from unstructured web with [AgentQL](https://www.agentql.com/). - AgentRPC Logo **[AgentRPC](https://github.com/agentrpc/agentrpc)** - Connect to any function, any language, across network boundaries using [AgentRPC](https://www.agentrpc.com/). - Aiven Logo **[Aiven](https://github.com/Aiven-Open/mcp-aiven)** - Navigate your [Aiven projects](https://go.aiven.io/mcp-server) and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services -- Algolia Logo **[Algolia MCP](https://github.com/algolia/mcp-node)** - Connect to a [AnalyticDB for MySQL](https://www.alibabacloud.com/en/product/analyticdb-for-mysql) Algolia MCP Server exposes a natural language interface to query, inspect, and manage Algolia indices and configs. Useful for monitoring, debugging and optimizing search performance within your agentic workflows. See [demo](https://www.youtube.com/watch?v=UgCOLcDI9Lg). +- Algolia Logo **[Algolia MCP](https://github.com/algolia/mcp-node)** Algolia MCP Server exposes a natural language interface to query, inspect, and manage Algolia indices and configs. Useful for monitoring, debugging and optimizing search performance within your agentic workflows. See [demo](https://www.youtube.com/watch?v=UgCOLcDI9Lg). - Alibaba Cloud AnalyticDB for MySQL Logo **[Alibaba Cloud AnalyticDB for MySQL](https://github.com/aliyun/alibabacloud-adb-mysql-mcp-server)** - Connect to a [AnalyticDB for MySQL](https://www.alibabacloud.com/en/product/analyticdb-for-mysql) cluster for getting database or table metadata, querying and analyzing data.It will be supported to add the openapi for cluster operation in the future. - Apache IoTDB Logo **[Apache IoTDB](https://github.com/apache/iotdb-mcp-server)** - MCP Server for [Apache IoTDB](https://github.com/apache/iotdb) database and its tools - Apify Logo **[Apify](https://github.com/apify/actors-mcp-server)** - [Actors MCP Server](https://apify.com/apify/actors-mcp-server): Use 3,000+ pre-built cloud tools to extract data from websites, e-commerce, social media, search engines, maps, and more From 8f64aad816ee5d324234a03eebb512c9840bd121 Mon Sep 17 00:00:00 2001 From: svkaizoku Date: Wed, 14 May 2025 23:18:10 +0200 Subject: [PATCH 05/28] Update README.md Add BVG Mcp Server --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index de01e8ee..a50461c9 100644 --- a/README.md +++ b/README.md @@ -499,6 +499,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[YouTube](https://github.com/ZubeidHendricks/youtube-mcp-server)** - Comprehensive YouTube API integration for video management, Shorts creation, and analytics. - **[Zoom](https://github.com/Prathamesh0901/zoom-mcp-server/tree/main)** - Create, update, read and delete your zoom meetings. - **[mcp_weather](https://github.com/isdaniel/mcp_weather_server)** - Get weather information from https://api.open-meteo.com API. +- **[BVG MCP Server - (Unofficial) ](https://github.com/svkaizoku/mcp-bvg)** - Unofficial MCP server for Berliner Verkehrsbetriebe Api. ## 📚 Frameworks From 082f38b5d29ae33b8d9df5d141d900e3eee9f026 Mon Sep 17 00:00:00 2001 From: Pavindu Lakshan Date: Thu, 15 May 2025 17:02:40 +0530 Subject: [PATCH 06/28] Add Asgardeo MCP server --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index de01e8ee..c71f2dc5 100644 --- a/README.md +++ b/README.md @@ -49,6 +49,7 @@ Official integrations are maintained by companies building production ready MCP - Apify Logo **[Apify](https://github.com/apify/actors-mcp-server)** - [Actors MCP Server](https://apify.com/apify/actors-mcp-server): Use 3,000+ pre-built cloud tools to extract data from websites, e-commerce, social media, search engines, maps, and more - APIMatic Logo **[APIMatic MCP](https://github.com/apimatic/apimatic-validator-mcp)** - APIMatic MCP Server is used to validate OpenAPI specifications using [APIMatic](https://www.apimatic.io/). The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API. - Arize-Phoenix Logo **[Arize Phoenix](https://github.com/Arize-ai/phoenix/tree/main/js/packages/phoenix-mcp)** - Inspect traces, manage prompts, curate datasets, and run experiments using [Arize Phoenix](https://github.com/Arize-ai/phoenix), an open-source AI and LLM observability tool. +- Asgardeo Logo **[Asgardeo](https://github.com/asgardeo/asgardeo-mcp-server)** - MCP server to interact with your [Asgardeo](https://wso2.com/asgardeo) organization through LLM tools. - DataStax logo **[Astra DB](https://github.com/datastax/astra-db-mcp)** - Comprehensive tools for managing collections and documents in a [DataStax Astra DB](https://www.datastax.com/products/datastax-astra) NoSQL database with a full range of operations such as create, update, delete, find, and associated bulk actions. - Atlan Logo **[Atlan](https://github.com/atlanhq/agent-toolkit/tree/main/modelcontextprotocol)** - The Atlan Model Context Protocol server allows you to interact with the [Atlan](https://www.atlan.com/) services through multiple tools. - Audiense Logo **[Audiense Insights](https://github.com/AudienseCo/mcp-audiense-insights)** - Marketing insights and audience analysis from [Audiense](https://www.audiense.com/products/audiense-insights) reports, covering demographic, cultural, influencer, and content engagement analysis. From 0f6e21e4cd8562843c22f4496d03400868d16d61 Mon Sep 17 00:00:00 2001 From: Taylor Wilsdon Date: Sat, 17 May 2025 12:27:06 -0400 Subject: [PATCH 07/28] Add Google Workspace MCP To my knowledge this would reflect the first and only Streamable HTTP transport Google Workspace MCP and an appealing option to those looking for a single platform to manage their Google Workspace accounts, as currently only an option for Sheets or Calendar exists as a standalone here. --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 6618738a..0001d549 100644 --- a/README.md +++ b/README.md @@ -300,6 +300,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Google Sheets](https://github.com/rohans2/mcp-google-sheets)** - A MCP Server written in TypeScript to access and edit data in your Google Sheets. - **[Google Tasks](https://github.com/zcaceres/gtasks-mcp)** - Google Tasks API Model Context Protocol Server. - **[Google Vertex AI Search](https://github.com/ubie-oss/mcp-vertexai-search)** - Provides Google Vertex AI Search results by grounding a Gemini model with your own private data +- **[Google Workspace](https://github.com/taylorwilsdon/google_workspace_mcp)** - Comprehensive Google Workspace MCP with full support for Calendar, Drive, Gmail, and Docs using Streamable HTTP or SSE transport. - **[GraphQL Schema](https://github.com/hannesj/mcp-graphql-schema)** - Allow LLMs to explore large GraphQL schemas without bloating the context. - **[HDW LinkedIn](https://github.com/horizondatawave/hdw-mcp-server)** - Access to profile data and management of user account with [HorizonDataWave.ai](https://horizondatawave.ai/). - **[Heurist Mesh Agent](https://github.com/heurist-network/heurist-mesh-mcp-server)** - Access specialized web3 AI agents for blockchain analysis, smart contract security, token metrics, and blockchain interactions through the [Heurist Mesh network](https://github.com/heurist-network/heurist-agent-framework/tree/main/mesh). From 145f893108cce6fb7a67199f91501a725aa33efc Mon Sep 17 00:00:00 2001 From: cliffhall Date: Thu, 22 May 2025 11:41:16 -0400 Subject: [PATCH 08/28] Allow multiple connections to the `everything` server. For both sse and streamableHttp, a server instance needs to be created for each transport. Otherwise, when a new client connects and its new transport is connected to the single server, the previous transport is overwritten in the server instance and can no longer communicate. * In sse.ts - remove global server, cleanup, and transport vars - add transports map - in sse GET handler, - check for sessionId, there shouldn't be one, so comment "Reconnecting?" and do nothing if present - if sessionId not present - create new server and transport instance - connect server to transport - add transport to transports map - in server.onclose, delete the transport from the transports map and call cleanup - in /message POST handler - get the sessionId from the request - get the transport from the map by sessionId - handle the message if the transport was found * In streamableHttp.ts - remove the global server and cleanup vars - change transports var to Map - in /mcp POST handler - when creating a new session - create a server instance - in server.onclose, delete the transport from the transports map and call cleanup - remove the calls to cleanup and server.close in the SIGINT handler, because the transport is closed and its onclose handler closes the server. --- src/everything/sse.ts | 50 +++++++++++++++++++------------- src/everything/streamableHttp.ts | 40 +++++++++++++------------ 2 files changed, 51 insertions(+), 39 deletions(-) diff --git a/src/everything/sse.ts b/src/everything/sse.ts index 01794cdd..a3eddaa5 100644 --- a/src/everything/sse.ts +++ b/src/everything/sse.ts @@ -6,36 +6,46 @@ console.error('Starting SSE server...'); const app = express(); -const { server, cleanup } = createServer(); - -let transport: SSEServerTransport; +const transports: Map = new Map(); app.get("/sse", async (req, res) => { - console.error("Received connection"); - transport = new SSEServerTransport("/message", res); - await server.connect(transport); + let transport: SSEServerTransport; + const { server, cleanup } = createServer(); - server.onclose = async () => { - await cleanup(); - await server.close(); - }; + if (req?.query?.sessionId) { + const sessionId = (req?.query?.sessionId as string) || "none"; + transport = transports.get(sessionId) as SSEServerTransport; + console.error("Client Reconnecting? ", transport.sessionId); + } else { + // Create and store transport for new session + transport = new SSEServerTransport("/message", res); + transports.set(transport.sessionId, transport); + + // Connect server to transport + await server.connect(transport); + console.error("Client Connected: ", transport.sessionId); + + // Handle close of connection + server.onclose = async () => { + console.error("Client Disconnected: ", transport.sessionId); + transports.delete(transport.sessionId); + await cleanup(); + }; + + } }); app.post("/message", async (req, res) => { - console.error("Received message"); - - await transport.handlePostMessage(req, res); -}); - -process.on("SIGINT", async () => { - await cleanup(); - await server.close(); - process.exit(0); + const sessionId = (req?.query?.sessionId as string) || "none"; + const transport = transports.get(sessionId); + if (transport) { + console.error("Client Message from", sessionId); + await transport.handlePostMessage(req, res); + } }); const PORT = process.env.PORT || 3001; app.listen(PORT, () => { console.error(`Server is running on port ${PORT}`); }); - diff --git a/src/everything/streamableHttp.ts b/src/everything/streamableHttp.ts index 9ea3a8fc..ccd3ad8a 100644 --- a/src/everything/streamableHttp.ts +++ b/src/everything/streamableHttp.ts @@ -8,9 +8,7 @@ console.error('Starting Streamable HTTP server...'); const app = express(); -const { server, cleanup } = createServer(); - -const transports: { [sessionId: string]: StreamableHTTPServerTransport } = {}; +const transports: Map = new Map(); app.post('/mcp', async (req: Request, res: Response) => { console.error('Received MCP POST request'); @@ -19,10 +17,13 @@ app.post('/mcp', async (req: Request, res: Response) => { const sessionId = req.headers['mcp-session-id'] as string | undefined; let transport: StreamableHTTPServerTransport; - if (sessionId && transports[sessionId]) { + if (sessionId && transports.has(sessionId)) { // Reuse existing transport - transport = transports[sessionId]; + transport = transports.get(sessionId)!; } else if (!sessionId) { + + const { server, cleanup } = createServer(); + // New initialization request const eventStore = new InMemoryEventStore(); transport = new StreamableHTTPServerTransport({ @@ -32,16 +33,18 @@ app.post('/mcp', async (req: Request, res: Response) => { // Store the transport by session ID when session is initialized // This avoids race conditions where requests might come in before the session is stored console.error(`Session initialized with ID: ${sessionId}`); - transports[sessionId] = transport; + transports.set(sessionId, transport); } }); + // Set up onclose handler to clean up transport when closed - transport.onclose = () => { + server.onclose = async () => { const sid = transport.sessionId; - if (sid && transports[sid]) { + if (sid && transports.has(sid)) { console.error(`Transport closed for session ${sid}, removing from transports map`); - delete transports[sid]; + transports.delete(sid); + await cleanup(); } }; @@ -87,7 +90,7 @@ app.post('/mcp', async (req: Request, res: Response) => { app.get('/mcp', async (req: Request, res: Response) => { console.error('Received MCP GET request'); const sessionId = req.headers['mcp-session-id'] as string | undefined; - if (!sessionId || !transports[sessionId]) { + if (!sessionId || !transports.has(sessionId)) { res.status(400).json({ jsonrpc: '2.0', error: { @@ -107,14 +110,14 @@ app.get('/mcp', async (req: Request, res: Response) => { console.error(`Establishing new SSE stream for session ${sessionId}`); } - const transport = transports[sessionId]; - await transport.handleRequest(req, res); + const transport = transports.get(sessionId); + await transport!.handleRequest(req, res); }); // Handle DELETE requests for session termination (according to MCP spec) app.delete('/mcp', async (req: Request, res: Response) => { const sessionId = req.headers['mcp-session-id'] as string | undefined; - if (!sessionId || !transports[sessionId]) { + if (!sessionId || !transports.has(sessionId)) { res.status(400).json({ jsonrpc: '2.0', error: { @@ -129,8 +132,8 @@ app.delete('/mcp', async (req: Request, res: Response) => { console.error(`Received session termination request for session ${sessionId}`); try { - const transport = transports[sessionId]; - await transport.handleRequest(req, res); + const transport = transports.get(sessionId); + await transport!.handleRequest(req, res); } catch (error) { console.error('Error handling session termination:', error); if (!res.headersSent) { @@ -161,14 +164,13 @@ process.on('SIGINT', async () => { for (const sessionId in transports) { try { console.error(`Closing transport for session ${sessionId}`); - await transports[sessionId].close(); - delete transports[sessionId]; + await transports.get(sessionId)!.close(); + transports.delete(sessionId); } catch (error) { console.error(`Error closing transport for session ${sessionId}:`, error); } } - await cleanup(); - await server.close(); + console.error('Server shutdown complete'); process.exit(0); }); From 0e702aa21cab5cb727a20f994860602030a859a2 Mon Sep 17 00:00:00 2001 From: Massimo Gatti Date: Tue, 20 May 2025 09:12:32 -0700 Subject: [PATCH 09/28] Add Microsoft Dataverse MCP Server --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 615076d4..7860fee2 100644 --- a/README.md +++ b/README.md @@ -132,6 +132,7 @@ Official integrations are maintained by companies building production ready MCP - Memgraph Logo **[Memgraph](https://github.com/memgraph/mcp-memgraph)** - Query your data in [Memgraph](https://memgraph.com/) graph database. - **[Metoro](https://github.com/metoro-io/metoro-mcp-server)** - Query and interact with kubernetes environments monitored by Metoro - Microsoft Clarity Logo **[Microsoft Clarity](https://github.com/microsoft/clarity-mcp-server)** - Official MCP Server to get your behavioral analytics data and insights from [Clarity](https://clarity.microsoft.com) +- Microsoft Dataverse Logo **[Microsoft Dataverse](https://go.microsoft.com/fwlink/?linkid=2320176)** - Chat over your business data using NL - Discover tables, run queries, retrieve data, insert or update records, and execute custom prompts grounded in business knowledge and context. - **[Milvus](https://github.com/zilliztech/mcp-server-milvus)** - Search, Query and interact with data in your Milvus Vector Database. - **[Momento](https://github.com/momentohq/mcp-momento)** - Momento Cache lets you quickly improve your performance, reduce costs, and handle load at any scale. - **[MongoDB](https://github.com/mongodb-js/mongodb-mcp-server)** - Both MongoDB Community Server and MongoDB Atlas are supported. From e22f665a00d4b6260acf785426f3d4388f16e9d1 Mon Sep 17 00:00:00 2001 From: Cheng Leong Ng Date: Wed, 28 May 2025 23:04:25 +0800 Subject: [PATCH 10/28] chore: update readme to add mcp-rag-local mcp server --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 59afb314..a775b03f 100644 --- a/README.md +++ b/README.md @@ -469,6 +469,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[QuickChart](https://github.com/GongRzhe/Quickchart-MCP-Server)** - A Model Context Protocol server for generating charts using QuickChart.io - **[Qwen_Max](https://github.com/66julienmartin/MCP-server-Qwen_Max)** - A Model Context Protocol (MCP) server implementation for the Qwen models. - **[RabbitMQ](https://github.com/kenliao94/mcp-server-rabbitmq)** - The MCP server that interacts with RabbitMQ to publish and consume messages. +- **[RAG Local](https://github.com/renl/mcp-rag-local)** - This MCP server for storing and retrieving text passages locally based on their semantic meaning. - **[RAG Web Browser](https://github.com/apify/mcp-server-rag-web-browser)** An MCP server for Apify's open-source RAG Web Browser [Actor](https://apify.com/apify/rag-web-browser) to perform web searches, scrape URLs, and return content in Markdown. - **[Raindrop.io](https://github.com/hiromitsusasaki/raindrop-io-mcp-server)** - An integration that allows LLMs to interact with Raindrop.io bookmarks using the Model Context Protocol (MCP). - **[Reaper](https://github.com/dschuler36/reaper-mcp-server)** - Interact with your [Reaper](https://www.reaper.fm/) (Digital Audio Workstation) projects. From 9ffacb78abbb607e9fb8903e74c13e532edd8615 Mon Sep 17 00:00:00 2001 From: cliffhall Date: Wed, 28 May 2025 11:13:54 -0400 Subject: [PATCH 11/28] Be more verbose about unexpected GET /sse calls from already connected clients. --- src/everything/sse.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/everything/sse.ts b/src/everything/sse.ts index a3eddaa5..671c2c17 100644 --- a/src/everything/sse.ts +++ b/src/everything/sse.ts @@ -15,7 +15,7 @@ app.get("/sse", async (req, res) => { if (req?.query?.sessionId) { const sessionId = (req?.query?.sessionId as string) || "none"; transport = transports.get(sessionId) as SSEServerTransport; - console.error("Client Reconnecting? ", transport.sessionId); + console.error("Client Reconnecting? This shouldn't happen; when client has a sessionId, GET /sse should not be called again.", transport.sessionId); } else { // Create and store transport for new session transport = new SSEServerTransport("/message", res); From 2da9f339694c5098ddc4355ac0f9410a46a14344 Mon Sep 17 00:00:00 2001 From: cliffhall Date: Wed, 28 May 2025 16:31:21 -0400 Subject: [PATCH 12/28] Remove or clause for sessionId where "none" is offered as an alternative. In the first case (line 16) we already know that req.query.sessionId is set to something. I n the second (line 40), it doesn't matter because if it doesn't map to a transport no further action is taken. --- src/everything/sse.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/everything/sse.ts b/src/everything/sse.ts index 671c2c17..3ee623c8 100644 --- a/src/everything/sse.ts +++ b/src/everything/sse.ts @@ -13,7 +13,7 @@ app.get("/sse", async (req, res) => { const { server, cleanup } = createServer(); if (req?.query?.sessionId) { - const sessionId = (req?.query?.sessionId as string) || "none"; + const sessionId = (req?.query?.sessionId as string); transport = transports.get(sessionId) as SSEServerTransport; console.error("Client Reconnecting? This shouldn't happen; when client has a sessionId, GET /sse should not be called again.", transport.sessionId); } else { @@ -37,7 +37,7 @@ app.get("/sse", async (req, res) => { }); app.post("/message", async (req, res) => { - const sessionId = (req?.query?.sessionId as string) || "none"; + const sessionId = (req?.query?.sessionId as string); const transport = transports.get(sessionId); if (transport) { console.error("Client Message from", sessionId); From 3adf59409c1b8fda19cca36b96774e3cedfb909b Mon Sep 17 00:00:00 2001 From: cliffhall Date: Wed, 28 May 2025 17:29:42 -0400 Subject: [PATCH 13/28] In sse.ts, /message endpoint, if transport isn't found for the given sessionId, output a "No transport found for sessionId" message. --- src/everything/sse.ts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/everything/sse.ts b/src/everything/sse.ts index 3ee623c8..a657af75 100644 --- a/src/everything/sse.ts +++ b/src/everything/sse.ts @@ -42,6 +42,8 @@ app.post("/message", async (req, res) => { if (transport) { console.error("Client Message from", sessionId); await transport.handlePostMessage(req, res); + } else { + console.error(`No transport found for sessionId ${sessionId}`) } }); From 7d093663244c640e41831350395366e36178e7e6 Mon Sep 17 00:00:00 2001 From: rututaj-browserstack Date: Thu, 29 May 2025 13:54:21 +0530 Subject: [PATCH 14/28] Add BrowserStack integration to README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 397948e5..a2dbd67a 100644 --- a/README.md +++ b/README.md @@ -63,6 +63,7 @@ Official integrations are maintained by companies building production ready MCP - Bitrise Logo **[Bitrise](https://github.com/bitrise-io/bitrise-mcp)** - Chat with your builds, CI, and [more](https://bitrise.io/blog/post/chat-with-your-builds-ci-and-more-introducing-the-bitrise-mcp-server). - Box Logo **[Box](https://github.com/box-community/mcp-server-box)** - Interact with the Intelligent Content Management platform through Box AI. - Browserbase Logo **[Browserbase](https://github.com/browserbase/mcp-server-browserbase)** - Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more) +- BrowserStack Logo **[BrowserStack](https://github.com/browserstack/mcp-server)** - Access BrowserStack's [Test Platform](https://www.browserstack.com/test-platform) to debug, write and fix tests, do accessibility testing and more. - PortSwigger Logo **[Burp Suite](https://github.com/PortSwigger/mcp-server)** - MCP Server extension allowing AI clients to connect to [Burp Suite](https://portswigger.net) - Cartesia logo **[Cartesia](https://github.com/cartesia-ai/cartesia-mcp)** - Connect to the [Cartesia](https://cartesia.ai/) voice platform to perform text-to-speech, voice cloning etc. - **[Chargebee](https://github.com/chargebee/agentkit/tree/main/modelcontextprotocol)** - MCP Server that connects AI agents to [Chargebee platform](https://www.chargebee.com). From bcd25241b67e09fefcca44efa4a50ac59836f3b5 Mon Sep 17 00:00:00 2001 From: cliffhall Date: Thu, 29 May 2025 13:31:33 -0400 Subject: [PATCH 15/28] Removing version-check.yml from .github/workflows. It checked the version of the now removed Github server and is breaking CI. --- .github/workflows/version-check.yml | 30 ----------------------------- 1 file changed, 30 deletions(-) delete mode 100644 .github/workflows/version-check.yml diff --git a/.github/workflows/version-check.yml b/.github/workflows/version-check.yml deleted file mode 100644 index b327649f..00000000 --- a/.github/workflows/version-check.yml +++ /dev/null @@ -1,30 +0,0 @@ -name: Version Consistency Check - -on: - push: - branches: - - main - pull_request: - release: - types: [published] - -jobs: - github: - name: Check GitHub server version consistency - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v4 - - - name: Check version consistency - run: | - PACKAGE_VERSION=$(node -p "require('./src/github/package.json').version") - TS_VERSION=$(grep -o '".*"' ./src/github/common/version.ts | tr -d '"') - - if [ "$PACKAGE_VERSION" != "$TS_VERSION" ]; then - echo "::error::Version mismatch detected!" - echo "::error::package.json version: $PACKAGE_VERSION" - echo "::error::version.ts version: $TS_VERSION" - exit 1 - else - echo "✅ Versions match: $PACKAGE_VERSION" - fi From 4610086a7f8983e29f4258ae362a114ba932e11f Mon Sep 17 00:00:00 2001 From: Jagannath Saragadam Date: Mon, 19 May 2025 10:11:15 -0700 Subject: [PATCH 16/28] add Alation MCP server --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index a91e092f..4618b6af 100644 --- a/README.md +++ b/README.md @@ -49,6 +49,7 @@ Official integrations are maintained by companies building production ready MCP - AgentQL Logo **[AgentQL](https://github.com/tinyfish-io/agentql-mcp)** - Enable AI agents to get structured data from unstructured web with [AgentQL](https://www.agentql.com/). - AgentRPC Logo **[AgentRPC](https://github.com/agentrpc/agentrpc)** - Connect to any function, any language, across network boundaries using [AgentRPC](https://www.agentrpc.com/). - Aiven Logo **[Aiven](https://github.com/Aiven-Open/mcp-aiven)** - Navigate your [Aiven projects](https://go.aiven.io/mcp-server) and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services +- Alation Logo **[Alation](https://github.com/Alation/alation-ai-agent-sdk)** - The Alation MCP server enables AI agents to access and leverage metadata from the [Alation Data Catalog](https://alation.com/). - Alibaba Cloud RDS MySQL Logo **[Alibaba Cloud RDS](https://github.com/aliyun/alibabacloud-rds-openapi-mcp-server)** - An MCP server designed to interact with the Alibaba Cloud RDS OpenAPI, enabling programmatic management of RDS resources via an LLM. - Alibaba Cloud AnalyticDB for MySQL Logo **[Alibaba Cloud AnalyticDB for MySQL](https://github.com/aliyun/alibabacloud-adb-mysql-mcp-server)** - Connect to a [AnalyticDB for MySQL](https://www.alibabacloud.com/en/product/analyticdb-for-mysql) cluster for getting database or table metadata, querying and analyzing data.It will be supported to add the openapi for cluster operation in the future. - Alibaba Cloud OPS Logo **[Alibaba Cloud OPS](https://github.com/aliyun/alibaba-cloud-ops-mcp-server)** - Manage the lifecycle of your Alibaba Cloud resources with [CloudOps Orchestration Service](https://www.alibabacloud.com/en/product/oos) and Alibaba Cloud OpenAPI. From 08b7d7a83d8cf6d02bb51d8af443f859b74f07fe Mon Sep 17 00:00:00 2001 From: Jagannath Saragadam Date: Mon, 19 May 2025 10:59:21 -0700 Subject: [PATCH 17/28] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 4618b6af..a0d8e357 100644 --- a/README.md +++ b/README.md @@ -49,7 +49,7 @@ Official integrations are maintained by companies building production ready MCP - AgentQL Logo **[AgentQL](https://github.com/tinyfish-io/agentql-mcp)** - Enable AI agents to get structured data from unstructured web with [AgentQL](https://www.agentql.com/). - AgentRPC Logo **[AgentRPC](https://github.com/agentrpc/agentrpc)** - Connect to any function, any language, across network boundaries using [AgentRPC](https://www.agentrpc.com/). - Aiven Logo **[Aiven](https://github.com/Aiven-Open/mcp-aiven)** - Navigate your [Aiven projects](https://go.aiven.io/mcp-server) and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services -- Alation Logo **[Alation](https://github.com/Alation/alation-ai-agent-sdk)** - The Alation MCP server enables AI agents to access and leverage metadata from the [Alation Data Catalog](https://alation.com/). +- Alation Logo **[Alation](https://github.com/Alation/alation-ai-agent-sdk)** - Unlock the power of the enterprise Data Catalog by harnessing tools provided by the Alation MCP server. - Alibaba Cloud RDS MySQL Logo **[Alibaba Cloud RDS](https://github.com/aliyun/alibabacloud-rds-openapi-mcp-server)** - An MCP server designed to interact with the Alibaba Cloud RDS OpenAPI, enabling programmatic management of RDS resources via an LLM. - Alibaba Cloud AnalyticDB for MySQL Logo **[Alibaba Cloud AnalyticDB for MySQL](https://github.com/aliyun/alibabacloud-adb-mysql-mcp-server)** - Connect to a [AnalyticDB for MySQL](https://www.alibabacloud.com/en/product/analyticdb-for-mysql) cluster for getting database or table metadata, querying and analyzing data.It will be supported to add the openapi for cluster operation in the future. - Alibaba Cloud OPS Logo **[Alibaba Cloud OPS](https://github.com/aliyun/alibaba-cloud-ops-mcp-server)** - Manage the lifecycle of your Alibaba Cloud resources with [CloudOps Orchestration Service](https://www.alibabacloud.com/en/product/oos) and Alibaba Cloud OpenAPI. From c59a2a898a3d39101f4bdc61b7252a4648693442 Mon Sep 17 00:00:00 2001 From: Jagannath Saragadam Date: Tue, 20 May 2025 12:38:32 -0700 Subject: [PATCH 18/28] sticky image URL --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index a0d8e357..bde6b7db 100644 --- a/README.md +++ b/README.md @@ -49,7 +49,7 @@ Official integrations are maintained by companies building production ready MCP - AgentQL Logo **[AgentQL](https://github.com/tinyfish-io/agentql-mcp)** - Enable AI agents to get structured data from unstructured web with [AgentQL](https://www.agentql.com/). - AgentRPC Logo **[AgentRPC](https://github.com/agentrpc/agentrpc)** - Connect to any function, any language, across network boundaries using [AgentRPC](https://www.agentrpc.com/). - Aiven Logo **[Aiven](https://github.com/Aiven-Open/mcp-aiven)** - Navigate your [Aiven projects](https://go.aiven.io/mcp-server) and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services -- Alation Logo **[Alation](https://github.com/Alation/alation-ai-agent-sdk)** - Unlock the power of the enterprise Data Catalog by harnessing tools provided by the Alation MCP server. +- Alation Logo **[Alation](https://github.com/Alation/alation-ai-agent-sdk)** - Unlock the power of the enterprise Data Catalog by harnessing tools provided by the Alation MCP server. - Alibaba Cloud RDS MySQL Logo **[Alibaba Cloud RDS](https://github.com/aliyun/alibabacloud-rds-openapi-mcp-server)** - An MCP server designed to interact with the Alibaba Cloud RDS OpenAPI, enabling programmatic management of RDS resources via an LLM. - Alibaba Cloud AnalyticDB for MySQL Logo **[Alibaba Cloud AnalyticDB for MySQL](https://github.com/aliyun/alibabacloud-adb-mysql-mcp-server)** - Connect to a [AnalyticDB for MySQL](https://www.alibabacloud.com/en/product/analyticdb-for-mysql) cluster for getting database or table metadata, querying and analyzing data.It will be supported to add the openapi for cluster operation in the future. - Alibaba Cloud OPS Logo **[Alibaba Cloud OPS](https://github.com/aliyun/alibaba-cloud-ops-mcp-server)** - Manage the lifecycle of your Alibaba Cloud resources with [CloudOps Orchestration Service](https://www.alibabacloud.com/en/product/oos) and Alibaba Cloud OpenAPI. From 77b7a16aae9ad7eeaac31429e2e4eceb67e5dd99 Mon Sep 17 00:00:00 2001 From: jeff nasseri Date: Tue, 13 May 2025 19:49:29 +0200 Subject: [PATCH 19/28] Add Helm Chart CLI to README.md as a new entry for AI interaction with Helm package manager --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index a91e092f..eecbc5ac 100644 --- a/README.md +++ b/README.md @@ -336,6 +336,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[GraphQL Schema](https://github.com/hannesj/mcp-graphql-schema)** - Allow LLMs to explore large GraphQL schemas without bloating the context. - **[HDW LinkedIn](https://github.com/horizondatawave/hdw-mcp-server)** - Access to profile data and management of user account with [HorizonDataWave.ai](https://horizondatawave.ai/). - **[Heurist Mesh Agent](https://github.com/heurist-network/heurist-mesh-mcp-server)** - Access specialized web3 AI agents for blockchain analysis, smart contract security, token metrics, and blockchain interactions through the [Heurist Mesh network](https://github.com/heurist-network/heurist-agent-framework/tree/main/mesh). +- **[Helm Chart CLI](https://github.com/jeff-nasseri/helm-chart-cli-mcp)** - Helm MCP provides a bridge between AI assistants and the Helm package manager for Kubernetes. It allows AI assistants to interact with Helm through natural language requests, executing commands like installing charts, managing repositories, and more. - **[Holaspirit](https://github.com/syucream/holaspirit-mcp-server)** - Interact with [Holaspirit](https://www.holaspirit.com/). - **[Home Assistant](https://github.com/tevonsb/homeassistant-mcp)** - Interact with [Home Assistant](https://www.home-assistant.io/) including viewing and controlling lights, switches, sensors, and all other Home Assistant entities. - **[Home Assistant](https://github.com/voska/hass-mcp)** - Docker-ready MCP server for Home Assistant with entity management, domain summaries, automation support, and guided conversations. Includes pre-built container images for easy installation. From 9206c2cbc276c79337eacd07737795dec6fb0c0b Mon Sep 17 00:00:00 2001 From: jeff nasseri Date: Thu, 29 May 2025 22:59:47 +0200 Subject: [PATCH 20/28] Move Helm Chart CLI entry to correct alphabetical position - Moved Helm Chart CLI before Heurist Mesh Agent to maintain alphabetical order - Follows repository convention of keeping community servers alphabetically sorted --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index eecbc5ac..7c1defab 100644 --- a/README.md +++ b/README.md @@ -335,8 +335,8 @@ A growing set of community-developed and maintained servers demonstrates various - **[Google Vertex AI Search](https://github.com/ubie-oss/mcp-vertexai-search)** - Provides Google Vertex AI Search results by grounding a Gemini model with your own private data - **[GraphQL Schema](https://github.com/hannesj/mcp-graphql-schema)** - Allow LLMs to explore large GraphQL schemas without bloating the context. - **[HDW LinkedIn](https://github.com/horizondatawave/hdw-mcp-server)** - Access to profile data and management of user account with [HorizonDataWave.ai](https://horizondatawave.ai/). -- **[Heurist Mesh Agent](https://github.com/heurist-network/heurist-mesh-mcp-server)** - Access specialized web3 AI agents for blockchain analysis, smart contract security, token metrics, and blockchain interactions through the [Heurist Mesh network](https://github.com/heurist-network/heurist-agent-framework/tree/main/mesh). - **[Helm Chart CLI](https://github.com/jeff-nasseri/helm-chart-cli-mcp)** - Helm MCP provides a bridge between AI assistants and the Helm package manager for Kubernetes. It allows AI assistants to interact with Helm through natural language requests, executing commands like installing charts, managing repositories, and more. +- **[Heurist Mesh Agent](https://github.com/heurist-network/heurist-mesh-mcp-server)** - Access specialized web3 AI agents for blockchain analysis, smart contract security, token metrics, and blockchain interactions through the [Heurist Mesh network](https://github.com/heurist-network/heurist-agent-framework/tree/main/mesh). - **[Holaspirit](https://github.com/syucream/holaspirit-mcp-server)** - Interact with [Holaspirit](https://www.holaspirit.com/). - **[Home Assistant](https://github.com/tevonsb/homeassistant-mcp)** - Interact with [Home Assistant](https://www.home-assistant.io/) including viewing and controlling lights, switches, sensors, and all other Home Assistant entities. - **[Home Assistant](https://github.com/voska/hass-mcp)** - Docker-ready MCP server for Home Assistant with entity management, domain summaries, automation support, and guided conversations. Includes pre-built container images for easy installation. From 29453343da482ecadbb5f0330ff387512556f580 Mon Sep 17 00:00:00 2001 From: Ram Rohit Gannavarapu Date: Thu, 29 May 2025 15:03:57 -0700 Subject: [PATCH 21/28] add github's official mcp server --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index a91e092f..d7210f95 100644 --- a/README.md +++ b/README.md @@ -101,6 +101,7 @@ Official integrations are maintained by companies building production ready MCP - Financial Datasets Logo **[Financial Datasets](https://github.com/financial-datasets/mcp-server)** - Stock market API made for AI agents - Firecrawl Logo **[Firecrawl](https://github.com/mendableai/firecrawl-mcp-server)** - Extract web data with [Firecrawl](https://firecrawl.dev) - Fireproof Logo **[Fireproof](https://github.com/fireproof-storage/mcp-database-server)** - Immutable ledger database with live synchronization +- **[Github](https://github.com/github/github-mcp-server)** - GitHub's official MCP Server - GibsonAI Logo **[GibsonAI](https://github.com/GibsonAI/mcp)** - AI-Powered Cloud databases: Build, migrate, and deploy database instances with AI - Gitea Logo **[Gitea](https://gitea.com/gitea/gitea-mcp)** - Interact with Gitea instances with MCP. - Gitee Logo **[Gitee](https://github.com/oschina/mcp-gitee)** - Gitee API integration, repository, issue, and pull request management, and more. From 31e04a829c4245d9a8957c1f6fba4e240e9b81e5 Mon Sep 17 00:00:00 2001 From: Pablo Zamudio Date: Fri, 30 May 2025 14:52:54 -0300 Subject: [PATCH 22/28] Add Mercado Pago's official MCP Server --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index bd8b5d05..fb0d0b1f 100644 --- a/README.md +++ b/README.md @@ -138,6 +138,7 @@ Official integrations are maintained by companies building production ready MCP - Meilisearch Logo **[Meilisearch](https://github.com/meilisearch/meilisearch-mcp)** - Interact & query with Meilisearch (Full-text & semantic search API) - Memgraph Logo **[Memgraph](https://github.com/memgraph/mcp-memgraph)** - Query your data in [Memgraph](https://memgraph.com/) graph database. - **[Metoro](https://github.com/metoro-io/metoro-mcp-server)** - Query and interact with kubernetes environments monitored by Metoro +- MercadoPago Logo **[Mercado Pago](https://mcp.mercadopago.com/)** - Mercado Pago's official MCP server. - Microsoft Clarity Logo **[Microsoft Clarity](https://github.com/microsoft/clarity-mcp-server)** - Official MCP Server to get your behavioral analytics data and insights from [Clarity](https://clarity.microsoft.com) - Microsoft Dataverse Logo **[Microsoft Dataverse](https://go.microsoft.com/fwlink/?linkid=2320176)** - Chat over your business data using NL - Discover tables, run queries, retrieve data, insert or update records, and execute custom prompts grounded in business knowledge and context. - **[Milvus](https://github.com/zilliztech/mcp-server-milvus)** - Search, Query and interact with data in your Milvus Vector Database. From becca06d0f7b313a518ec1a253b7d5794afbb943 Mon Sep 17 00:00:00 2001 From: Encore Shao Date: Sun, 1 Jun 2025 16:27:40 +0800 Subject: [PATCH 23/28] feat: add bambooHR MCP to community servers list --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 1c3d279f..a0dfbca0 100644 --- a/README.md +++ b/README.md @@ -190,6 +190,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Azure ADX](https://github.com/pab1it0/adx-mcp-server)** - Query and analyze Azure Data Explorer databases. - **[Azure DevOps](https://github.com/Vortiago/mcp-azure-devops)** - An MCP server that provides a bridge to Azure DevOps services, enabling AI assistants to query and manage work items. - **[Baidu AI Search](https://github.com/baidubce/app-builder/tree/master/python/mcp_server/ai_search)** - Web search with Baidu Cloud's AI Search +- **[BambooHR MCP](https://github.com/encoreshao/bamboohr-mcp)** - An MCP server that interfaces with the BambooHR APIs, providing access to employee data, time tracking, and HR management features. - **[Base Free USDC Transfer](https://github.com/magnetai/mcp-free-usdc-transfer)** - Send USDC on [Base](https://base.org) for free using Claude AI! Built with [Coinbase CDP](https://docs.cdp.coinbase.com/mpc-wallet/docs/welcome). * **[Basic Memory](https://github.com/basicmachines-co/basic-memory)** - Local-first knowledge management system that builds a semantic graph from Markdown files, enabling persistent memory across conversations with LLMs. - **[BigQuery](https://github.com/LucasHild/mcp-server-bigquery)** (by LucasHild) - This server enables LLMs to inspect database schemas and execute queries on BigQuery. From 3e33e4eb18538b9950ee4eb69e56b96ae956720b Mon Sep 17 00:00:00 2001 From: svkaizoku Date: Sun, 1 Jun 2025 14:32:21 +0200 Subject: [PATCH 24/28] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index c0e5f567..23b1ef9c 100644 --- a/README.md +++ b/README.md @@ -246,6 +246,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[BreakoutRoom](https://github.com/agree-able/room-mcp)** - Agents accomplishing goals together in p2p rooms - **[browser-use](https://github.com/co-browser/browser-use-mcp-server)** (by co-browser) - browser-use MCP server with dockerized playwright + chromium + vnc. supports stdio & resumable http. - **[Bsc-mcp](https://github.com/TermiX-official/bsc-mcp)** The first MCP server that serves as the bridge between AI and BNB Chain, enabling AI agents to execute complex on-chain operations through seamless integration with the BNB Chain, including transfer, swap, launch, security check on any token and even more. +- **[BVG MCP Server - (Unofficial) ](https://github.com/svkaizoku/mcp-bvg)** - Unofficial MCP server for Berliner Verkehrsbetriebe Api. - **[Calculator](https://github.com/githejie/mcp-server-calculator)** - This server enables LLMs to use calculator for precise numerical calculations. - **[CFBD API](https://github.com/lenwood/cfbd-mcp-server)** - An MCP server for the [College Football Data API](https://collegefootballdata.com/). - **[ChatMCP](https://github.com/AI-QL/chat-mcp)** – An Open Source Cross-platform GUI Desktop application compatible with Linux, macOS, and Windows, enabling seamless interaction with MCP servers across dynamically selectable LLMs, by **[AIQL](https://github.com/AI-QL)** @@ -565,7 +566,6 @@ A growing set of community-developed and maintained servers demonstrates various - **[YouTube Video Summarizer](https://github.com/nabid-pf/youtube-video-summarizer-mcp)** - Summarize lengthy youtube videos. - **[Zoom](https://github.com/Prathamesh0901/zoom-mcp-server/tree/main)** - Create, update, read and delete your zoom meetings. - **[mcp_weather](https://github.com/isdaniel/mcp_weather_server)** - Get weather information from https://api.open-meteo.com API. -- **[BVG MCP Server - (Unofficial) ](https://github.com/svkaizoku/mcp-bvg)** - Unofficial MCP server for Berliner Verkehrsbetriebe Api. ## 📚 Frameworks From 57588a139fe3449bf29a1080d482901e2ef869d8 Mon Sep 17 00:00:00 2001 From: Samuel Colvin Date: Sun, 1 Jun 2025 17:15:12 +0100 Subject: [PATCH 25/28] add pydantic mcp-run-python --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 5016bee1..c294f045 100644 --- a/README.md +++ b/README.md @@ -478,6 +478,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Pulumi](https://github.com/dogukanakkaya/pulumi-mcp-server)** - MCP Server to Interact with Pulumi API, creates and lists Stacks - **[Puppeteer vision](https://github.com/djannot/puppeteer-vision-mcp)** - Use Puppeteer to browse a webpage and return a high quality Markdown. Use AI vision capabilities to handle cookies, captchas, and other interactive elements automatically. - **[Pushover](https://github.com/ashiknesin/pushover-mcp)** - Send instant notifications to your devices using [Pushover.net](https://pushover.net/) +- **[pydantic/pydantic-ai/mcp-run-python](https://github.com/pydantic/pydantic-ai/tree/main/mcp-run-python)** - Run Python code in a secure sandbox via MCP tool calls, powered by Deno and Pyodide - **[Quarkus](https://github.com/quarkiverse/quarkus-mcp-servers)** - MCP servers for the Quarkus Java framework. - **[QGIS](https://github.com/jjsantos01/qgis_mcp)** - connects QGIS to Claude AI through the MCP. This integration enables prompt-assisted project creation, layer loading, code execution, and more. - **[QuickChart](https://github.com/GongRzhe/Quickchart-MCP-Server)** - A Model Context Protocol server for generating charts using QuickChart.io From 2f319965c2680e4ef7f0dbb128d3d8c0d16083e5 Mon Sep 17 00:00:00 2001 From: s l Date: Mon, 2 Jun 2025 17:48:57 +0800 Subject: [PATCH 26/28] add wavespeed mcp --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index c294f045..206c5ea6 100644 --- a/README.md +++ b/README.md @@ -196,6 +196,7 @@ Official integrations are maintained by companies building production ready MCP - Verodat Logo **[Verodat](https://github.com/Verodat/verodat-mcp-server)** - Interact with Verodat AI Ready Data platform - VeyraX Logo **[VeyraX](https://github.com/VeyraX/veyrax-mcp)** - Single tool to control all 100+ API integrations, and UI components - WayStation Logo **[WayStation](https://github.com/waystation-ai/mcp)** - Universal MCP server to connect to popular productivity tools such as Notion, Monday, AirTable, and many more +- WaveSpeed Logo **[WaveSpeed](https://github.com/WaveSpeedAI/mcp-server)** - WaveSpeed MCP server providing AI agents with image and video generation capabilities. - Xero Logo **[Xero](https://github.com/XeroAPI/xero-mcp-server)** - Interact with the accounting data in your business using our official MCP server - YugabyteDB Logo **[YugabyteDB](https://github.com/yugabyte/yugabytedb-mcp-server)** - MCP Server to interact with your [YugabyteDB](https://www.yugabyte.com/) database - Zapier Logo **[Zapier](https://zapier.com/mcp)** - Connect your AI Agents to 8,000 apps instantly. From 95d0a3a4383f71b089cef2c84eb2a024d40eb62c Mon Sep 17 00:00:00 2001 From: cliffhall Date: Mon, 2 Jun 2025 13:56:28 -0400 Subject: [PATCH 27/28] Update the archived server links to point to their actual locations in the servers-archived repo rather than the now invalid locations in this repo. Also, removed the link to the git server which, while it still exists in the archived repo, is still alive and well in this one. --- README.md | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/README.md b/README.md index b5932f86..c2b91778 100644 --- a/README.md +++ b/README.md @@ -23,20 +23,19 @@ These servers aim to demonstrate MCP features and the TypeScript and Python SDKs The following reference servers are now archived and can be found at [servers-archived](https://github.com/modelcontextprotocol/servers-archived). -- **[AWS KB Retrieval](src/aws-kb-retrieval-server)** - Retrieval from AWS Knowledge Base using Bedrock Agent Runtime -- **[Brave Search](src/brave-search)** - Web and local search using Brave's Search API -- **[EverArt](src/everart)** - AI image generation using various models -- **[Git](src/git)** - Tools to read, search, and manipulate Git repositories -- **[GitHub](src/github)** - Repository management, file operations, and GitHub API integration -- **[GitLab](src/gitlab)** - GitLab API, enabling project management -- **[Google Drive](src/gdrive)** - File access and search capabilities for Google Drive -- **[Google Maps](src/google-maps)** - Location services, directions, and place details -- **[PostgreSQL](src/postgres)** - Read-only database access with schema inspection -- **[Puppeteer](src/puppeteer)** - Browser automation and web scraping -- **[Redis](src/redis)** - Interact with Redis key-value stores -- **[Sentry](src/sentry)** - Retrieving and analyzing issues from Sentry.io -- **[Slack](src/slack)** - Channel management and messaging capabilities -- **[Sqlite](src/sqlite)** - Database interaction and business intelligence capabilities +- **[AWS KB Retrieval](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/aws-kb-retrieval-server)** - Retrieval from AWS Knowledge Base using Bedrock Agent Runtime +- **[Brave Search](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/brave-search)** - Web and local search using Brave's Search API +- **[EverArt](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/everart)** - AI image generation using various models +- **[GitHub](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/github)** - Repository management, file operations, and GitHub API integration +- **[GitLab](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/gitlab)** - GitLab API, enabling project management +- **[Google Drive](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/gdrive)** - File access and search capabilities for Google Drive +- **[Google Maps](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/google-maps)** - Location services, directions, and place details +- **[PostgreSQL](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/postgres)** - Read-only database access with schema inspection +- **[Puppeteer](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/puppeteer)** - Browser automation and web scraping +- **[Redis](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/redis)** - Interact with Redis key-value stores +- **[Sentry](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/sentry)** - Retrieving and analyzing issues from Sentry.io +- **[Slack](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/slack)** - Channel management and messaging capabilities +- **[Sqlite](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/sqlite)** - Database interaction and business intelligence capabilities ## 🤝 Third-Party Servers From 28bd5a4b0c37988f17c28a2fb626ed074561a429 Mon Sep 17 00:00:00 2001 From: cliffhall Date: Mon, 2 Jun 2025 14:21:17 -0400 Subject: [PATCH 28/28] Add git back to the reference servers list --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index c2b91778..08405e13 100644 --- a/README.md +++ b/README.md @@ -15,6 +15,7 @@ These servers aim to demonstrate MCP features and the TypeScript and Python SDKs - **[Everything](src/everything)** - Reference / test server with prompts, resources, and tools - **[Fetch](src/fetch)** - Web content fetching and conversion for efficient LLM usage - **[Filesystem](src/filesystem)** - Secure file operations with configurable access controls +- **[Git](src/git)** - Tools to read, search, and manipulate Git repositories - **[Memory](src/memory)** - Knowledge graph-based persistent memory system - **[Sequential Thinking](src/sequentialthinking)** - Dynamic and reflective problem-solving through thought sequences - **[Time](src/time)** - Time and timezone conversion capabilities