- Home
- MCP servers
- Biel.ai
Biel.ai
- python
2
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
The Biel.ai MCP Server lets AI tools access your product documentation through Biel.ai’s hosted Retrieval-Augmented Generation layer. This makes smart code completions, accurate technical answers, and context-aware suggestions possible directly in your IDE or chat tools by querying your docs and knowledge base.
How to use
Connect your AI tools to Biel.ai with a configured MCP server and then add that server to each tool you use. You’ll be able to ask questions like what the auth headers are for a given endpoint or request contextual product knowledge as you work.
How to install
Prerequisites: you need a Biel.ai account and a Biel project set up to enable the remote MCP server URL.
- Create or confirm your MCP configuration with the following server entry.
{
"mcpServers": {
"biel_ai": {
"description": "Query your product's documentation, APIs, and knowledge base.",
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.biel.ai/sse?project_slug=YOUR_PROJECT_SLUG&domain=https://your-docs-domain.com"
]
}
}
}
Additional setup for the client apps
Add the configured MCP server to each AI tool you plan to use.
Cursor: Settings → Tools & Integrations → New MCP server.
Claude Desktop: Edit claude_desktop_config.json.
VS Code: Install the MCP extension.
Start asking questions
Ask questions to verify your setup and confirm endpoints, headers, or behavior. For example: Can you check in Biel AI what the auth headers are for the /users endpoint?
Self-hosting (Optional)
If you prefer to run your own MCP server instance locally or in your environment, you have two common options: local development or Docker-based deployment.
Local development
# Clone and run locally
git clone https://github.com/techdocsStudio/biel-mcp
cd biel-mcp
pip install -r requirements.txt
python biel_mcp_server.py
Docker deployment
Use Docker to run the MCP server. You can build an image or use docker-compose for convenience.
# Docker Compose (recommended)
docker-compose up -d --build
# Or Docker directly
docker build -t biel-mcp .
docker run -d -p 7832:7832 biel-mcp
Notes on access and keys
A Biel.ai account and project are required. If you have private projects, include an API key in the MCP config when needed.
Available tools
Cursor
Integrates Biel.ai MCP server with Cursor to query product docs and knowledge base via the MCP URL.
ClaudeDesktop
Configures Claude Desktop to use the Biel.ai MCP server through claude_desktop_config.json.
VSCode MCP Extension
Enables MCP connections inside Visual Studio Code to fetch knowledge from Biel.ai during edits and coding sessions.