mcp-rag-bridge

Item: mcp-rag-bridge
Rating: 74
Author: M8ven

Enables AI agents to query and manage a document knowledge base via MCP, with RAG-powered search and grounded answers with citations.

→ zyay/mcp-rag-bridge · listed on glama

Emerging. Nothing concerning found — the project is young, and grades cap until reputation is earned through real adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for the top badge — read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Verified

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

🚨

Secret credentials may flow to a network call

1 flow detected: OPENAI_API_KEY. We can’t prove the destination matches the brand the credential belongs to.

🔐

You'll be asked for 1 credential: OPENAI_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run. Since this is a local server, you set these in your own MCP client configuration and they stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configRAG_CHUNK_SIZE— 600 Text chunk size (chars)

configRAG_CHUNK_OVERLAP— 120 Overlap between chunks

configRAG_EMBEDDING_MODEL

configRAG_CHROMA_DIR— .chroma Vector store path

configRAG_COLLECTION— docs ChromaDB collection name

configRAG_DATA_DIR— data Document directory

configLLM_PROVIDER— OpenAI fallback: Set =openai and OPENAI_API_KEY=sk-...

configOLLAMA_URL

configOLLAMA_MODEL— Ollama (default): Local, free, no API key. Set =llama3.2.

🔐 secretOPENAI_API_KEY— OpenAI fallback: Set LLM_PROVIDER=openai and =sk-...

configOPENAI_MODEL— gpt-4o-mini OpenAI model name

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 3 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/zyay-mcp-rag-bridge-1icfa1)](https://m8ven.ai/mcp/zyay-mcp-rag-bridge-1icfa1)

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: 2e149405270d3a0eeb30d6c50163510720e64502

code hash: 3f96b5f618bec3e62c83c31e60159273bf7bbde2a7f595bfbea42dda70f2570e

verified: 8/13/2026, 7:40:02 AM

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client