MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Bayesian memory that learns from feedback for LLM agents
MIT ★ 9 -
code-review-botgithub.com/SManojna/code-review-botupdated this year
LangGraph ReAct agent that reviews GitHub PRs — fetches diffs, retrieves similar past reviews via pgvector, posts context-aware comments through a custom MCP server, and learns from user feedback. Deployed on Cloud Run.
-
skill-context-managergithub.com/Mavis2103/skill-context-managerupdated this year
Context-aware skill selection for AI agents — solves the 'too many skills' problem. Reduces skill context tokens by 85-98%, improves selection accuracy, learns from feedback.
MIT ★ 1 -
Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proofs, 25 extractors, 23 MCP tools. Gets smarter with use.
Apache-2.0 ★ 24