Rag MCP Server

Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup

Local serverstdioPython

What is the Rag MCP server?

Rag MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup.

What you get

RAG Vault lets your AI coding assistant search your private documents, things like API specs, research papers, and internal docs. Everything runs locally and your data stays on your machine unless you choose to pull in content from a remote URL.

What the assistant can call

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

  • Advanced — The Advanced tool exposed by this server

Configuration and credentials

You will need 8 environment variables: BASE_DIR, DB_PATH, CACHE_DIR, RAG_EMBEDDING_DEVICE, RAG_HYBRID_WEIGHT, RAG_GROUPING, MODEL_NAME, RAG_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

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

Choosing this one

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Rag's toolset — Advanced — is a fair guide to whether it matches your workflow. It is maintained by RobThePCGuy; worth a glance at recent repository activity before you build anything load-bearing on it.

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

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.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the rag mcp server does with a few real requests.

Available tools

ToolWhat it does
AdvancedThe Advanced tool exposed by this server.

How to install the Rag MCP server

{
  "mcpServers": {
    "local-rag": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "github:RobThePCGuy/rag-vault"],
      "env": {
        "BASE_DIR": "/path/to/your/documents"
      }
    }
  }
}

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

Configuration

VariableDescriptionRequired
BASE_DIRFilesystem location the server is allowed to use.Optional
DB_PATHFilesystem location the server is allowed to use.Optional
CACHE_DIRFilesystem location the server is allowed to use.Optional
RAG_EMBEDDING_DEVICEConfiguration value read at startup.Optional
RAG_HYBRID_WEIGHTConfiguration value read at startup.Optional
RAG_GROUPINGConfiguration value read at startup.Optional
MODEL_NAMEConfiguration value read at startup.Optional
RAG_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Rag to Advanced.

Frequently asked questions

It connects Rag to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Advanced) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Rag directly.