Ragie runs on your own machine — the client starts it, so there is no endpoint to ping. 217 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": {
"command": "uvx",
"args": [
"mcparmory-ragie"
]
}
}
}
[mcp_servers.ragie]
command = "uvx"
args = ["mcparmory-ragie"]
{
"mcpServers": {
"ragie": {
"command": "uvx",
"args": [
"mcparmory-ragie"
]
}
}
}
{
"servers": {
"ragie": {
"type": "stdio",
"command": "uvx",
"args": [
"mcparmory-ragie"
]
}
}
}
Run WhatsApp AI agents: manage agents, conversations, CRM contacts, orders and RAG docs.
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.
Local vector and raster editing engine for agents: layered documents, saved sessions and exports.
Release management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs
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.
Answers built from our own checks of this server.