{
  "markdown": "<div align=\"center\">\n  <picture>\n    <source media=\"(prefers-color-scheme: dark)\" srcset=\"./logo-dark.png\" />\n    <img alt=\"Biel.ai\" src=\"./logo.png\" width=\"120\" />\n  </picture>\n  <h1>Biel.ai MCP Server</h1>\n  <h3>Connect your IDE to your product docs</h3>\n</div>\n\n\nGive AI tools like Cursor, VS Code, and Claude Desktop access to your company's product knowledge through the [Biel.ai platform](https://biel.ai).\n\nBiel.ai provides a hosted Retrieval-Augmented Generation (RAG) layer that makes your documentation searchable and useful to AI tools. This enables smarter completions, accurate technical answers, and context-aware suggestions—directly in your IDE or chat environment.\n\n![Demo](./demo.png)\n\nWhen AI tools can read your product documentation, they become **significantly** more helpful—generating more accurate code completions, answering technical questions with context, and guiding developers with real-time product knowledge.\n\n\n> **Note:** Requires a Biel.ai account and project setup. **[Start your free 15-day trial](https://app.biel.ai/accounts/signup/)**.\n\n<h3><a href=\"https://docs.biel.ai/integrations/mcp-server?utm_source=github&utm_medium=referral&utm_campaign=readme\">See quickstart instructions →</a></h3>\n\n## Getting started\n\n### 1. Get your MCP configuration\n\n```json\n{\n  \"mcpServers\": {\n    \"biel-ai\": {\n      \"description\": \"Query your product's documentation, APIs, and knowledge base.\",\n      \"command\": \"npx\",\n      \"args\": [\n        \"mcp-remote\",\n        \"https://mcp.biel.ai/sse?project_slug=YOUR_PROJECT_SLUG&domain=https://your-docs-domain.com\"\n      ]\n    }\n  }\n}\n```\n\n**Required:** `project_slug` and `domain`  \n**Optional:** `api_key` (only needed for private projects)\n\n### 2. Add to your AI tool\n\n* **Cursor**: **Settings** → **Tools & Integrations* → **New MCP server**.\n* **Claude Desktop**: Edit `claude_desktop_config.json`  \n* **VS Code**: Install **MCP extension**.\n\n### 3. Start asking questions\n\n```\nCan you check in biel_ai what the auth headers are for the /users endpoint?\n```\n\n## Self-hosting (Optional)\n\nFor advanced users who prefer to run their own MCP server instance:\n\n### Local development\n```bash\n# Clone and run locally\ngit clone https://github.com/TechDocsStudio/biel-mcp\ncd biel-mcp\npip install .\nbiel-mcp\n```\n\n### Use as a Python package\n\nApplications that host their own ASGI stack can install the server directly\nfrom a tagged revision and import its FastAPI application:\n\n```bash\npip install \"biel-mcp @ git+https://github.com/TechDocsStudio/biel-mcp.git@VERSION\"\n```\n\n```python\nfrom biel_mcp.server import app\n```\n\n### Docker deployment\n```bash\n# Docker Compose (recommended)\ndocker-compose up -d --build\n\n# Or Docker directly\ndocker build -t biel-mcp .\ndocker run -d -p 7832:7832 biel-mcp\n```\n\n## Support\n\n- **Issues**: [GitHub Issues](https://github.com/techdocsStudio/biel-mcp/issues)\n- **Contact**: [support@biel.ai](mailto:support@biel.ai)\n- **Custom Demo**: [Book a demo](https://biel.ai/contact)\n",
  "bytes": 2973,
  "sha": "89df9135ef4b92a58c74fefb3740b64599f69443de369793d396d1aea7594dca",
  "repo_slug": "techdocsstudio/biel-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_biel_biel_ai_ba3fbb67/readme"
}