MCP Doctor
This is quality assurance tooling for MCP server developers. It evaluates six dimensions of what the author calls "contract quality": task clarity, trust and safety declarations, interface design, token efficiency, install friction, and cross-platform metadata completeness. You can run it as a CLI tool that checks a local server path and outputs grades with recommendations, or wire it up as an MCP server so agents can evaluate other servers programmatically. Default mode is rule based and offline, but you can pass OPENAI_API_KEY to get AI enhanced qualitative reviews. Useful before publishing to registries like Smithery or when debugging why agents struggle to use your tools correctly.
- GitHub stars
- 1
- tools
- 2
- transport
- STDIO
- last updated
- Mar 1, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
check_serverRun all 6 checks. Use `mode="ai"` for LLM-enhanced review.
Run all 6 checks. Use `mode="ai"` for LLM-enhanced review.
No parameter schema in public metadata yet.
list_dimensionsList what MCP Doctor evaluates
List what MCP Doctor evaluates
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
mcp-doctor logo
MCP Doctor
Check and improve the contract quality of any MCP server — for humans, agents, and platforms.
Problem
Most MCP servers are built with only one audience in mind (usually human developers reading a README). But a successful MCP server needs to satisfy three audiences simultaneously:
Details
- Repository
- github.com/jiansen/mcp-doctor
- Package
mcp-doctor- Transport
- STDIO
- Registry
- MCP registry, active