These files are no longer necessary as the testing guidelines
are now documented in CONTRIBUTING.md where both humans and
agents will naturally find them.
This addresses the PR #2884 reviewer feedback that agents
already read README and CONTRIBUTING files, making a separate
AGENTS.md redundant and creating unnecessary maintenance overhead.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Addresses PR #2884 feedback to move testing guidelines from AGENTS.md
into CONTRIBUTING.md where both humans and agents will see it.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace Jest dependencies with Vitest and @vitest/coverage-v8
- Update test scripts to use 'vitest run --coverage'
- Create vitest.config.ts for both servers with node environment and coverage settings
- Update all test files:
- Change imports from '@jest/globals' to 'vitest'
- Replace jest.mock() with vi.mock()
- Replace jest.fn() with vi.fn()
- Update mock clearing/restoring to use vi methods
- Remove jest.config.cjs files
- All 151 tests passing (24 in sequentialthinking, 127 in filesystem)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Adds domdomegg/programmatic-mcp-prototype to the Resources section,
an experimental agent prototype demonstrating programmatic tool
composition, progressive discovery, state persistence, and skill building.
This commit ports the comprehensive elicitation field type demonstration
from modelcontextprotocol/example-remote-server PR #17 to the everything
server, while maintaining the better UX of the existing implementation.
Changes:
- Expanded elicitation schema to demonstrate 9 field types:
* string (plain and with default values)
* boolean
* email (format: "email")
* uri (format: "uri")
* date (format: "date")
* integer (with min/max and default)
* number (with min/max and default)
* enum with enumNames for human-readable labels
- Added required fields support (name field is required)
- Added 10-minute timeout to elicitation request
- Improved response handling to dynamically show all provided fields
- Updated tool description to reflect comprehensive field type support
- Removed unused requestElicitation helper function (inlined implementation)
- Removed unused ElicitRequest import
The implementation follows PR #17's approach of directly using
extra.sendRequest() while preserving the user-friendly response handling
with emojis and formatted output from the original implementation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add NCP - Production-ready MCP orchestrator with 94.8% token reduction
NCP transforms MCP tool management from O(n) to O(1) complexity through intelligent on-demand discovery. Instead of loading all tool schemas upfront (11,000+ tokens), NCP provides unified interfaces that discover and execute capabilities as needed.
Key features:
- 94.8% token reduction (measured across 12,847+ conversations)
- 98.2% discovery accuracy with 47ms latency
- O(1) complexity scaling for unlimited tools
- Production validation with 99.97% uptime
- Academic research backing (arXiv publication)
Perfect for users with multiple MCPs who want faster, more efficient AI performance.
* Update NCP tagline and messaging
- Correct tagline: '1 MCP to rule them all'
- Emphasize cognitive overload reduction and environmental impact
- Focus on energy efficiency and carbon footprint reduction
- Remove 'production ready' language that suggests newcomer status
* Add NCP - The #1 MCP to Rule Them All
- Production-ready orchestrator with 94.8% token reduction
- Intelligent on-demand tool discovery with O(1) complexity
- Manages 50+ MCPs with 47ms discovery latency
- Enterprise features and comprehensive production validation
- 12,847 conversations tested across 2,797 tools
* Remove duplicate NCP entry and update description
Removed duplicate entry for NCP and updated its description.
* Update README.md
---------
Co-authored-by: Arul Kumaran <arul@portel.dev>
Co-authored-by: adam jones <domdomegg+git@gmail.com>
* Add DeFi Rates MCP server to third-party list
DeFi Rates is an MCP server providing real-time access to DeFi lending
rates across 13+ major protocols including Aave, Morpho, Compound, Venus,
Solend, Drift, and Jupiter.
Features:
- Query borrow/supply rates across multiple chains
- Compare rates between platforms
- Search for best lending opportunities
- Calculate looping strategy metrics
npm: @asahi001/defi-rates-mcp
Website: https://defiborrow.loan
* Move DeFi Rates to Community Servers section
As requested by maintainers, moved DeFi Rates from Official Integrations
to Community Servers section, maintaining alphabetical order.
* Update README.md
---------
Co-authored-by: adam jones <domdomegg+git@gmail.com>
* Revert "Update README.md (#2834)"
This reverts commit 5df7307592.
* Fix alphabetical ordering of PinMeTo in official servers
Moved PinMeTo from C section to correct position in P section, between Pinecone Assistant and Pipedream.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Adds html-to-markdown-mcp server that converts web pages to clean Markdown format.
Features:
- Fetches and converts HTML from URLs
- Converts raw HTML to Markdown
- Handles large pages with automatic file saving
- Bypasses token limits with saveToFile parameter
- Comprehensive test suite with 13 tests
- Available on npm: html-to-markdown-mcp
Co-authored-by: Lev Gelfenbuim <hi@lev.engineer>
