Company Documents MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Company Documents MCP ServerAdd a document titled 'Q4 Report' with URL https://example.com and summarize it."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Company Documents MCP Server
This is a containerized Model Context Protocol (MCP) server designed to connect with Mistral agents. It manages a local SQLite database that stores company document metadata and URLs (e.g., Azure Blob Storage), and can automatically generate summaries using the Mistral OCR and Chat Completions API.
Requirements
Docker (for containerized deployment)
Python 3.12 (for local development)
A Mistral API Key (for document summarization)
Related MCP server: Doc Agent
How to Run (with Docker)
This is the recommended way to run the project.
1. Build the Docker Image:
docker build -t company_doc_mcp_server .2. Configure your Environment Variables:
Open the .env file located in the project directory and insert your actual MISTRAL_API_KEY:
MISTRAL_API_KEY=your_actual_key_here
MCP_TRANSPORT=sse3. Run the Container:
Pass the .env file to Docker using the --env-file flag.
Option A: Standard stdio (for local agents)
docker run -d \
--name mcp_server \
-v ~/mcp_data:/data \
--env-file .env \
company_doc_mcp_serverOption B: Server-Sent Events (SSE) (for remote HTTP connections, e.g., remote Mistral instances)
docker run -d \
--name mcp_server \
-v ~/mcp_data:/data \
-p 8000:8000 \
--env-file .env \
company_doc_mcp_server(Note: The -v ~/mcp_data:/data flag mounts a persistent folder on your host machine to store the SQLite database so it isn't lost when the container stops).
How to Run (Local Development / Without Docker)
If you just want to run it via standard Python on your machine:
1. Create a virtual environment and install dependencies:
python -m venv venv
# On Windows: venv\Scripts\activate
# On Mac/Linux: source venv/bin/activate
pip install -r requirements.txt2. Set your API Key:
# On Windows PowerShell
$env:MISTRAL_API_KEY="your_mistral_api_key_here"
# On Mac/Linux
export MISTRAL_API_KEY="your_mistral_api_key_here"3. Run the Server:
python src/server.py(Optionally set $env:MCP_TRANSPORT="sse" before running if you want HTTP instead of stdio).
This server cannot be deployed
Maintenance
Related MCP Connectors
Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.
- DatanemOAuthcom.datanem
Turn PDFs, scans and photos into a queryable database. Invoices, CVs, receipts, in bulk.
Ingest, manage, and retrieve documents for RAG-powered AI applications
PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.
Related MCP Servers
- FlicenseAqualityDmaintenanceParses PDF receipts to extract grocery and shopping expenses, automatically categorizes items using smart rules and LLM fallback, and stores them in a local SQLite database for querying purchase history and spending patterns.3-
- AlicenseNot gradedqualityDmaintenanceEnables extraction of structured data from documents like invoices, receipts, and bank statements using local Vision AI (Ollama) or cloud providers (Gemini), with data stored in a local SQLite database.10 npmMIT
- FlicenseNot gradedqualityDmaintenanceIndexes documentation sites by base URL and serves keyword search, optional semantic search, and Markdown page retrieval as MCP tools, all from a single SQLite file.-
- FlicenseAqualityDmaintenanceParses Italian INAZ payslip PDFs into a local SQLite database, enabling AI clients to analyze salary history, search items, and get detailed breakdowns while keeping data on your machine.51-