All of open source at your agent's fingertips.

A remote MCP server over the entire Code Genome corpus, growing to encompass all the world's provably used open-source code. Your agent navigates and reads it all as if every project were fully resolved in an IDE it could explore. Try any tool below, then connect your agent in one line.

Connect your agent

Which agent are you using?

Run in your terminal

claude mcp add --transport http codegenome https://api.codegenomeproject.org/mcp

Or add to .mcp.json in your project root

{
  "mcpServers": {
    "codegenome": {
      "type": "http",
      "url": "https://api.codegenomeproject.org/mcp"
    }
  }
}

Endpoint: https://api.codegenomeproject.org/mcp. Clients run the OAuth flow on first call — no token or header to paste.

The MCP tools

The exact tools your agent gets, with the exact descriptions it reads — pick one, then run it against the public corpus and read the JSON that comes back. The find_* and usage_examples tools resolve through the corpus’s type tables, so they catch what a grep or a docs pipe can’t.

Tool

Trigram code search

search(query, package?, language?, max?, offset?, context?, output_mode?, include_offsets?)

Trigram code search over the Code Genome corpus. query: plain text, /regex/, or type-reference filters ref: / ref.<kind>:. Scope with package (native coordinate, e.g. org.slf4j:slf4j-api:2.0.17, npm:@nestjs/core@10.3.0, requests==2.31.0) and/or language (one or more source languages), or omit for the whole corpus; then fetch_file to read a match in context.

Scope to one package by its native coordinate — Maven group:artifact:version, npm:@scope/name@version, or name==version for PyPI. Omit for the whole corpus.

Restrict to one or more source languages, OR’d together; omit for all languages.

matching lines

Context lines per match.

Include highlight byte-offsets.