MCP server setup
The Beakr MCP server connects your knowledge base to Claude Code, Cursor, and any AI assistant that supports the Model Context Protocol.
What is MCP?
The Model Context Protocol is an open standard for connecting AI assistants to external data sources and tools. The Beakr MCP server exposes 16 tools that give your AI assistant direct access to your knowledge base.
Get your API key
You need a Beakr API key for the MCP server. Go to thebeakr.com > Settings > API Keys tab > Create API Key. The key starts with bk_live_ and is shown only once.
Claude Code
Add to .mcp.json in your project root:
{
"mcpServers": {
"beakr": {
"command": "beakr",
"args": ["mcp"],
"env": {
"BEAKR_API_URL": "https://api.thebeakr.com",
"BEAKR_API_KEY": "<your-api-key>"
}
}
}
}Cursor
In Cursor, go to Settings > MCP Servers and add a new server with the same configuration:
| Field | Value |
|---|---|
| Command | beakr |
| Arguments | mcp |
| Environment | BEAKR_API_KEY=<your-key> |
Local development
For local development against a running Beakr API:
{
"mcpServers": {
"beakr": {
"command": "beakr",
"args": ["mcp"],
"env": {
"BEAKR_API_URL": "http://localhost:8000",
"BEAKR_DEV_IDENTITY": "seed_sarah",
"BEAKR_DEV_EMAIL": "sarah.chen@example.com",
"BEAKR_DEV_DISPLAY_NAME": "Sarah Chen"
}
}
}
}Verify
After configuring, your AI assistant should list beakr as a connected MCP server. You can test with:
# In Claude Code or Cursor, ask:
"Use the beakr research tool to tell me about recent decisions"The MCP server requires the CLI to be installed (pip install beakr-cli) and accessible on your PATH. No separate authentication is needed if you set BEAKR_API_KEY in the MCP config.