What it does

Queries a Ragie index: search documents, retrieve chunks with sources. The point of a managed retrieval layer is that chunking and embeddings are somebody else's problem. Check what the index actually contains before trusting an answer that cites nothing.

Install

Terminal

npx -y @ragieai/mcp-server

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "ragie": {
      "command": "npx",
      "args": [
        "-y",
        "@ragieai/mcp-server"
      ]
    }
  }
}

Use it for

Retrieval over documents you already indexed in Ragie

Skip it if

Teams without a Ragie corpus; there is nothing to retrieve

When to use it

Reach for this when the task needs rag inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Ragie MCP