Biel Ai MCP server
{
"mcpServers": {
"biel-ai": {
"type": "http",
"url": "https://mcp.biel.ai/v2/{project_slug}/mcp"
}
}
}{
"mcpServers": {
"biel-ai": {
"type": "http",
"url": "https://mcp.biel.ai/v2/{project_slug}/mcp"
}
}
}{
"mcpServers": {
"biel-ai": {
"type": "http",
"url": "https://mcp.biel.ai/v2/{project_slug}/mcp"
}
}
}{
"servers": {
"biel-ai": {
"type": "http",
"url": "https://mcp.biel.ai/v2/{project_slug}/mcp"
}
}
}{
"mcpServers": {
"biel-ai": {
"type": "http",
"url": "https://mcp.biel.ai/v2/{project_slug}/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 2.0.0
What it does
Biel.ai MCP Server connects AI tools like Cursor, VS Code, and Claude Desktop to your product documentation through a hosted RAG layer. It enables AI assistants to retrieve source-cited answers from your indexed documentation during development.
- Query product documentation and API specifications directly from your IDE while writing code.
- Get technical answers about your product features and endpoints with source citations.
- Provide context-aware suggestions and code completions based on your actual product knowledge.
Tools this server exposes
| Tool | Does |
|---|---|
| query_documentation | Search and retrieve information from your indexed product documentation with source citations. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.