Updated package.json and ran prettier

This commit is contained in:
cliffhall
2025-12-13 14:33:16 -05:00
parent 919b2e0138
commit a235ed8016
9 changed files with 24 additions and 14 deletions

View File

@@ -21,16 +21,16 @@
- Handle errors with try/catch blocks and provide clear error messages
- Use consistent indentation (2 spaces) and trailing commas in multi-line objects
- Match existing code style, import order, and module layout in the respective folder.
- Use camelCase for variables/functions,
- Use PascalCase for types/classes,
- Use camelCase for variables/functions,
- Use PascalCase for types/classes,
- Use UPPER_CASE for constants
- Use kebab-case for file names and registered tools, prompts, and resources.
- Use verbs for tool names, e.g., `get-annotated-message` instead of `annotated-message`
## Extending the Server
The Everything Server is designed to be extended at well-defined points.
See [Extension Points](docs/extension.md) and [Project Structure](docsstructure.md).
The Everything Server is designed to be extended at well-defined points.
See [Extension Points](docs/extension.md) and [Project Structure](docsstructure.md).
The server factory is `src/everything/server/index.ts` and registers all features during startup as well as handling post-connection setup.
### High-level

View File

@@ -1,4 +1,5 @@
# Everything Server Architecture
**Architecture
| [Project Structure](structure.md)
| [Startup Process](startup.md)
@@ -12,14 +13,17 @@ It explains how the server starts, how transports are wired, where tools, prompt
## Highlevel Overview
### Purpose
A minimal, modular MCP server showcasing core Model Context Protocol features. It exposes simple tools, prompts, and resources, and can be run over multiple transports (STDIO, SSE, and Streamable HTTP).
### Design
A small “server factory” constructs the MCP server and registers features.
Transports are separate entry points that create/connect the server and handle network concerns.
A small “server factory” constructs the MCP server and registers features.
Transports are separate entry points that create/connect the server and handle network concerns.
Tools, prompts, and resources are organized in their own submodules.
### Multiclient
The server supports multiple concurrent clients. Tracking per session data is demonstrated with
resource subscriptions and simulated logging.

View File

@@ -1,4 +1,5 @@
# Everything Server - Extension Points
**[Architecture](architecture.md)
| [Project Structure](structure.md)
| [Startup Process](startup.md)

View File

@@ -1,4 +1,5 @@
# Everything Server - Features
**[Architecture](architecture.md)
| [Project Structure](structure.md)
| [Startup Process](startup.md)

View File

@@ -1,4 +1,5 @@
# Everything Server - How It Works
**[Architecture](architecture.md)
| [Project Structure](structure.md)
| [Startup Process](startup.md)

View File

@@ -1,4 +1,5 @@
# Everything Server LLM Instructions
**[Architecture](architecture.md) | [Project Structure](structure.md) | [Startup Process](startup.md) | [Server Features](features.md) | [Extension Points](extension.md) | [How It Works](how-it-works.md)**
Audience: These instructions are written for an LLM or autonomous agent integrating with the Everything MCP Server. Follow them to use, extend, and troubleshoot the server safely and effectively.
@@ -10,10 +11,11 @@ Date: 2025-12-13
You are speaking MCP. Always prefer discovering server capabilities dynamically and follow the MCP spec. The Everything server exposes prompts, tools, resources, logging, and subscriptions. It may run over `stdio`, SSE (deprecated), or Streamable HTTP.
Discover features:
- Prompts: `prompts/list` → then `prompts/get` with `name` and `arguments`.
- Tools: `tools/list` → then call tools via `tools/call` with validated params.
- Resources: `resources/list` → then `resources/read { uri }`.
- Logging: `logging/setLevel`set desired log level if supported by your client SDK; otherwise just read logs returned by tool/prompts as content parts.
- Prompts: `prompts/list` → then `prompts/get` with `name` and `arguments`.
- Tools: `tools/list` → then call tools via `tools/call` with validated params.
- Resources: `resources/list` → then `resources/read { uri }`.
- Logging: `logging/setLevel`set desired log level if supported by your client SDK; otherwise just read logs returned by tool/prompts as content parts.
Behavioral guidelines:
@@ -21,7 +23,6 @@ Behavioral guidelines:
- Prefer idempotent reads first (resources, prompts) before mutating via tools.
- If the server provides instructions in the initialize result (this document), follow them over any prior assumptions.
## Troubleshooting
When things dont work, follow this checklist before making code changes.

View File

@@ -1,4 +1,5 @@
# Everything Server - Startup Process
**[Architecture](architecture.md)
| [Project Structure](structure.md)
| Startup Process

View File

@@ -1,4 +1,5 @@
# Everything Server - Project Structure
**[Architecture](architecture.md)
| Project Structure
| [Startup Process](startup.md)
@@ -68,7 +69,7 @@ src/everything
### `AGENTS.md`
- Directions for Agents/LLMs explaining coding guidelines and how to appropriately extend the server.
- Directions for Agents/LLMs explaining coding guidelines and how to appropriately extend the server.
### `package.json`

View File

@@ -25,8 +25,8 @@
"start:stdio": "node dist/index.js stdio",
"start:sse": "node dist/index.js sse",
"start:streamableHttp": "node dist/index.js streamableHttp",
"prettier-fix": "prettier --write .",
"prettier-check": "prettier --check ."
"prettier:fix": "prettier --write .",
"prettier:check": "prettier --check ."
},
"dependencies": {
"@modelcontextprotocol/sdk": "^1.24.3",