Ragie runs on your own machine — the client starts it, so there is no endpoint to ping. 261 installs a week from pypi. Last commit 12 May 2026.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Today is the operative word: we check Ragie every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ragie -- uvx mcparmory-ragie
{
"mcpServers": {
"ragie": {
"args": [
"mcparmory-ragie"
],
"command": "uvx"
}
}
}
[mcp_servers.ragie]
command = "uvx"
args = ["mcparmory-ragie"]
{
"mcpServers": {
"ragie": {
"args": [
"mcparmory-ragie"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"ragie": {
"args": [
"mcparmory-ragie"
],
"command": "uvx"
}
}
}
Local RAG MCP for markdown documentation. Retrieval only; host synthesizes answers.
Permission-aware RAG for agents — ingest docs, hybrid search, cited answers (hosted API).
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Manage your Mistral platform — models, files, batch jobs, agents and RAG document libraries.
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
Search and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks.
Dynamic RAG Engine preventing AI hallucinations in Korean Finance and Crypto markets.
Answers built from our own checks of this server.