ragie
local MCP serverragie is a local MCP server: Ingest, manage, and retrieve documents for RAG-powered AI applications. Install it from pypi as mcparmory-ragie.
Installation
Terminal
claude mcp add ragie -- uvx mcparmory-ragie
Run in your project folder. Add --scope user to use it everywhere.
Claude Desktop, Cursor & other clients
Add to claude_desktop_config.json or .cursor/mcp.json.
{
"mcpServers": {
"ragie": {
"command": "uvx",
"args": [
"mcparmory-ragie"
]
}
}
}What you need
- Runtime: Python with uv (runs with uvx) or Docker.
- MCP client: Claude Code, Codex, Antigravity, Claude Desktop, Cursor or any other client that speaks MCP over stdio.
Summary
Ingest, manage, and retrieve documents for RAG-powered AI applications
ragie vs similar servers
| Server | Stars | Type | API key | Runtime |
|---|---|---|---|---|
| ragie | 31 | Local | No | pypi |
| Docling MCP | 759 | Local | Yes | pypi |
| reMarkable MCP Server | 237 | Local | Yes | pypi |
| Auth0 MCP Server | 122 | Local | No | npm |
| Tripsy | 17 | Hosted | No | None |
Questions
No. The registry entry lists no keys or environment variables.
Python with uv (runs with uvx) or Docker, plus an MCP client such as Claude Code, Codex, Claude Desktop or Cursor.
ragie is a local MCP server distributed as the pypi package mcparmory-ragie.
Run: claude mcp add ragie -- uvx mcparmory-ragie
Run: codex mcp add ragie -- uvx mcparmory-ragie
Similar MCP servers
NameStars
- Docling MCPio.github.docling-project/docling-mcp759
- reMarkable MCP Serverio.github.SamMorrowDrums/remarkable237
- Auth0 MCP Servercom.auth0/mcp122
- Tripsyio.github.tripsyapp/tripsy17
- mcp-servercom.puter/mcp-server44K
- GitHubio.github.github/github-mcp-server33K
- Agent Skills Search Serverai.com.mcp/skills-search26K
- Skyvernio.github.Skyvern-AI/skyvern23K