Devrag MCP Server

DevRag is a lightweight RAG (Retrieval-Augmented Generation) system designed specifically for developers using Claude Code. Stop wasting tokens by

Local serverstdioPython

What is the Devrag MCP server?

DevRag is a lightweight RAG (Retrieval-Augmented Generation) system designed specifically for developers using Claude Code. Stop wasting tokens by reading entire documents - let vector search find exactly what you need. The devrag mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 6 defined tools rather than through you.

What it actually does

  • Wasting Context: Reading entire docs every time (3,000+ tokens per file)
  • Poor Searchability: Claude doesn't know which file contains what
  • Repetitive: Same documents read multiple times across sessions
  • 40x Less Tokens: Vector search retrieves only relevant chunks (~200 tokens)
  • 15x Faster: Search in 100ms vs 30 seconds of reading
  • Auto-Discovery: Claude Code finds documents without knowing file names

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Its toolset

Everything the assistant can do here goes through one of these:

  • search — // Search only in docs/api directory search(query: "user endpoints", directory: "docs/api")
  • index_markdown — The index_markdown tool exposed by this server
  • list_documents — The list_documents tool exposed by this server
  • delete_document — The delete_document tool exposed by this server
  • reindex_document — The reindex_document tool exposed by this server
  • Build — The Build tool exposed by this server

Configuration

You will need 2 environment variables: HTTP_PROXY, HTTPS_PROXY. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Go 1.21+ (for building from source) - CGO enabled (for sqlite-vec) - macOS, Linux, or Windows

Caveats

  • 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 devrag mcp server does with a few real requests.

When to reach for it

This sits in the file and storage access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Devrag's toolset — search, index_markdown, list_documents and 3 more — is a fair guide to whether it matches your workflow. It is maintained by tomohiro-owada; 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.

Available tools

ToolWhat it does
search// Search only in docs/api directory search(query: "user endpoints", directory: "docs/api")
index_markdownThe index_markdown tool exposed by this server.
list_documentsThe list_documents tool exposed by this server.
delete_documentThe delete_document tool exposed by this server.
reindex_documentThe reindex_document tool exposed by this server.
BuildThe Build tool exposed by this server.

How to install the Devrag MCP server

**Using a custom config file:**
```json
{
  "mcpServers": {
    "devrag": {
      "type": "stdio",
      "command": "/usr/local/bin/devrag",
      "args": ["--config", "/path/to/custom-config.json"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Go 1.21+ (for building from source) - CGO enabled (for sqlite-vec) - macOS, Linux, or Windows
VariableDescriptionRequired
HTTP_PROXYConfiguration value read at startup.Optional
HTTPS_PROXYConfiguration value read at startup.Optional

Example prompts to try

  • Use Devrag to search.
  • Use Devrag to index markdown.
  • Use Devrag to list documents.

Frequently asked questions

It connects Devrag to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (search, index_markdown, list_documents, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Devrag directly.