#6464th of 86 in MCP servers for developers
chunkhound
Semantic code search and cited research over a codebase and its git history
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 1.5k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Oct 2026
- Language
- Python
1,165 on 3 Apr 20261,456 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
ChunkHound indexes a repository with Tree-sitter and answers questions about it through a CLI, with source citations. It supports regex and semantic search, research over commit ranges, tags or the last N commits, and web search for external docs. Semantic search needs an embedding provider; deep research also needs an LLM provider.
Who it is for: Engineers giving coding agents or reviewers cited context on large codebases
Strengths
- Searches git history by last N commits, commit hash, tag or range
- Regex search works with no API keys or providers
- Ollama can serve embeddings locally, avoiding sending code to external services
- Parses many languages through Tree-sitter, including Python, TypeScript, Go, Rust and C/C++
Weaknesses
- Semantic search requires an embedding provider; deep research also needs an LLM and reranking
- Editor and agent integration is documented only on the external docs site
- README gives no RAM, index size or performance figures
- README states the code is 100% AI generated
What it needs
- Needs Python 3.10+, uv, VoyageAI, OpenAI or Ollama for embeddings, Claude Code CLI, Codex CLI, Anthropic, OpenAI or Grok for LLM
- Models: VoyageAI, OpenAI, Ollama, Anthropic, Grok
Quick answers
Is chunkhound open source?
Yes. Its code is on GitHub under the MIT license.
Also in MCP servers for developers
See all 86| Rank | Project | Score |
|---|---|---|
| 1 | codegraphLocal code knowledge graph that coding agents query over MCP | 96 out of 100 |
| 2 | gitnexusCode knowledge graph exposed to coding agents through MCP tools | 96 out of 100 |
| 3 | serenaMCP server giving coding agents symbol-level code search, editing and refactoring | 91 out of 100 |
| #4 | n8n-mcpMCP server exposing n8n node docs, templates and workflow management to AI assistants | 90 out of 100 |
| #5 | context7MCP server and CLI that feed current library docs to coding agents | 89 out of 100 |