Coderag MCP Server

Lightning-fast semantic code search with AST chunking (15+ languages) - Hybrid TF-IDF + Vector, MCP-ready for AI assistants

Remote serverstreamable-httpTypeScript

What is the Coderag MCP server?

Connect Coderag to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Lightning-fast semantic code search with AST chunking (15+ languages) - Hybrid TF-IDF + Vector, MCP-ready for AI assistants. The coderag mcp server is what makes that connection.

What the server does

This repository is product SSOT. Sibling agent tools live in separate repos (Citra · Iris · Cue · Spine · Lookout · Locus).

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Local-first — TF-IDF indexing runs on your machine; embeddings are optional and caller-configured
  • Doc — Purpose
  • Job — Find the right code chunk
  • Repocoderag
  • Need — What you get
  • query — string
  • limit — number
  • include_content — boolean
  • file_extensions — string[]
  • path_filter — string
  • exclude_paths — string[]
  • Package — Description

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Where it fits

Plenty of developer tooling 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. Coderag's toolset — Local-first, Doc, Job and 11 more — is a fair guide to whether it matches your workflow. It is maintained by SylphxAI; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Coderag.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Local-firstTF-IDF indexing runs on your machine; embeddings are optional and caller-configured.
DocPurpose
JobFind the right **code chunk**
Repo[coderag](https://github.com/SylphxAI/coderag)
NeedWhat you get
querystring
limitnumber
include_contentboolean
file_extensionsstring[]
path_filterstring
exclude_pathsstring[]
PackageDescription
TopicLink
ChannelStatus

How to install the Coderag MCP server

{
  "mcpServers": {
    "server-sylphxai": {
      "command": "npx",
      "args": ["-y", "@sylphx/locus"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Coderag to Local-first.
  • Use Coderag to Doc.
  • Use Coderag to Job.

Frequently asked questions

Coderag indexes project source files and provides a TF‑IDF‑based search tool (`codebase_search`) that returns ranked code snippets optimized for consumption by large language models.