Home › Search & Research › Ragmir
Ragmir
Cited local retrieval for agents: search code, PDFs, and Office files with exact citations.
Topics: end to end RAG platforms
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (npm 6.15.2)
npx -y @jcode.labs/[email protected]
Or add to your MCP client config:
{
"mcpServers": {
"ragmir": {
"command": "npx",
"args": [
"-y",
"@jcode.labs/[email protected]"
],
"env": {
"RAGMIR_PROJECT_ROOT": "<YOUR_VALUE>"
}
}
}
}
RAGMIR_PROJECT_ROOTrequired — Absolute path of the project whose Ragmir base the server reads
This server takes extra arguments — see its repository.
Package (oci)
docker run -i --rm ghcr.io/jcode-works/ragmir:6.15.2
Or add to your MCP client config:
{
"mcpServers": {
"ragmir": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/jcode-works/ragmir:6.15.2"
]
}
}
}
This server takes extra arguments — see its repository.
Related servers
vectara-mcp
Access Vectara's RAG-as-a-service platform.
Scholar RAG MCP
Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.
customgpt-mcp
Access the CustomGPT.ai RAG-as-a-service API.
mcp-ragchat
Add RAG-based AI chat to any website: local vector store, OpenAI, Anthropic or Gemini models, a self-contained chat server and an…
grounding-ai
Local searchable index of PDFs, EPUBs and Word documents for grounded answers with page and section citations.
ai·rete·rag
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry