@fyrn/mcp-server

MCP server for Fyrn — connect AI agents to your integration platform.

Implements the Model Context Protocol so AI assistants like Claude can manage your integrations, flows, connectors, and more.

Claude Desktop Setup

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "fyrn": {
      "command": "npx",
      "args": ["@fyrn/mcp-server"],
      "env": {
        "FYRN_AGENT_KEY": "<your-agent-key>",
        "FYRN_API_URL": "https://api.fyrn.ai"
      }
    }
  }
}

Get your agent key from the Fyrn dashboard under Settings > Agent Keys.

Environment Variables

| Variable | Required | Default | Description | |----------|----------|---------|-------------| | FYRN_AGENT_KEY | Yes | — | Agent API key for authentication | | FYRN_API_URL | No | https://api.fyrn.ai | Fyrn API base URL | | MCP_PORT | No | 3100 | Port for SSE transport mode |

Transport Modes

stdio (default) — communicates over stdin/stdout, used by Claude Desktop and most MCP clients:

fyrn-mcp --transport stdio

SSE — HTTP-based Server-Sent Events for web integrations:

fyrn-mcp --transport sse

Available Tools

The MCP server exposes tools in three permission tiers:

• Tier 1 (Read): List flows, get metrics, search, view messages, call published APIs
• Tier 2 (Build): Create flows, deploy, generate connectors, manage adapters
• Tier 3 (Manage): Retry messages, approve healing events, manage schedules, batch operations

Tool access is controlled by your agent key's permission tier.

Security

• Rate limiting (per-minute and daily quotas)
• Infinite loop detection
• PII filtering on message data
• Approval gates for destructive operations
• Full audit logging

Documentation

Full docs at docs.fyrn.ai