Chunkhound MCP Server

Chunkhound MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. .

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

What the assistant can call

Once Chunkhound is connected, these are the calls the assistant has available:

• Embeddings — VoyageAI (recommended) | OpenAI | Ollama (local)
• LLM — Claude Code CLI or Codex CLI (no key needed) | Anthropic | OpenAI |
• Autodoc — generate shareable docs from code-backed research
• Local — first indexing** — keep code search and indexing under your control
• multi — language codebases
• local — only or security-sensitive environments

Configuration and credentials

• Python 3.10+ - uv — install via curl -LsSf https://astral.sh/uv/install.sh | sh - API keys (optional — regex search works without any): - Embeddings: VoyageAI (recommended) | OpenAI | Ollama (local) - LLM: Claude Code CLI or Codex CLI (no key needed) |

Before you rely on it

• 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.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the chunkhound mcp server does with a few real requests.

Choosing this one

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Chunkhound's toolset — Embeddings, LLM, Autodoc and 3 more — is a fair guide to whether it matches your workflow. It is maintained by ofriw; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.