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.
-
rvue-mcpgithub.com/sriramfullstack/rvue-web-appupdated this year
MCP server for rvue team intelligence. Serves team conventions, anti-patterns, and domain knowledge to AI coding agents via the Model Context Protocol.
npm MIT -
kronodegithub.com/gauravgill90/kronodeupdated this year
Extract team conventions from git history, serve via MCP to any AI coding tool
pypi MIT -
Pilot — the rutter runtime. Serves your team's conventions and knowledge to AI coding agents via CLI and MCP.
MIT -
chameleongithub.com/crisnahine/chameleonupdated this year
Auto-derives codebase conventions from repo analysis and injects archetype-aware guidance into AI-generated code, enforcing team idioms, banned imports, and framework-specific patterns for TypeScript/JavaScript, Ruby, and Python projects.
MIT ★ 8 -
MCP server that gives AI coding agents a project's context (overview, conventions, security rules, features) and checks their code against the team's rules.
MIT -
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.
npm NOASSERTION ★ 68 -
Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving layer.
pypi MIT ★ 27 -
@codehabits/mcpgithub.com/codehabits-dev/codehabitsupdated this year
MCP server for codehabits: get_team_context, check_code, get_knowledge, and reviewer tools over stdio for Cursor, Claude Code, and MCP-compatible agents.
npm MIT -
MCP-powered, agentic commit workflow: AI agents (Claude Code, Cursor) and developers commit through your team rules. Checked, formatted and enforced on every commit.
npm MIT -
MCP server for Sqemo. AI agents query and edit ERDs, generate physical names from your team's shared glossary, import/export SQL (7 dialects) and DBML, and diff the model against a live database.
npm MIT