Codemunch MCP Server

Code indexing MCP: 13 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.

Local serverstdioPython

What is the Codemunch MCP server?

Most developer tooling work still happens through a UI a human drives. Codemunch MCP server moves it into the conversation instead. Code indexing MCP: 13 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.

The short version

Intelligent code indexing MCP server. 15 tools, 10 languages, tree-sitter AST extraction, hybrid search (FTS5 + vector), call graphs, remote repo indexing, incremental indexing.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • index_folder — Index a local directory (incremental, SHA-256 based)
  • index_repo — Index a GitHub/GitLab repo (tarball download, no git needed)
  • list_repos — List all indexed repositories with stats
  • invalidate_cache — Force re-index a repository
  • file_tree — Get directory tree with file counts
  • file_outline — List symbols in a single file
  • repo_outline — List all symbols in repo (summary)
  • get_symbol — Get full source of one symbol (O(1) byte seek)
  • get_symbols — Batch get multiple symbols
  • search_symbols — Hybrid search (FTS5 + vector RRF)
  • search_text — Full-text search in file contents
  • get_callees — What does this function call?

Getting it running

Installation goes through your MCP client rather than a global install: point it at codemunch-pro on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Codemunch's toolset — index_folder, index_repo, list_repos and 11 more — is a fair guide to whether it matches your workflow. It is maintained by BigJai; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Codemunch's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Codemunch.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
index_folderIndex a local directory (incremental, SHA-256 based)
index_repoIndex a GitHub/GitLab repo (tarball download, no git needed)
list_reposList all indexed repositories with stats
invalidate_cacheForce re-index a repository
file_treeGet directory tree with file counts
file_outlineList symbols in a single file
repo_outlineList all symbols in repo (summary)
get_symbolGet full source of one symbol (O(1) byte seek)
get_symbolsBatch get multiple symbols
search_symbolsHybrid search (FTS5 + vector RRF)
search_textFull-text search in file contents
get_calleesWhat does this function call?
get_callersWho calls this function?
diff_symbolsWhat changed since last index? (PR review)

How to install the Codemunch MCP server

{
  "mcpServers": {
    "codemunch-pro": {
      "command": "uvx",
      "args": ["codemunch-pro"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Codemunch to index folder.
  • Use Codemunch to index repo.
  • Use Codemunch to list repos.

Frequently asked questions

It connects Codemunch to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (index_folder, index_repo, list_repos, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Codemunch directly.