Plyto ships a hosted MCP server. Connect it once and your assistant can work your CRM directly: add contacts, move deals, draft emails and ad campaigns, pull reports: the same tools Plyto's own agent uses.
1Create an API key
In Plyto, open Settings → API keysand create a key. Keys are scoped to one business and inherit your role's permissions. Copy the key; it's shown once.
2Add the server to your client
Claude (claude.ai, desktop & mobile apps)
Go to Settings → Connectors → Add custom connector.
Server URL: https://plyto.ai/api/mcp
Open Request headers and add a header named Authorization with the value Bearer YOUR_API_KEY, including the space after “Bearer”.
Ask your assistant things like “add the lead from this email thread to my CRM”, “which deals are stalled?”, or “draft a follow-up sequence for contacts tagged webinar”. The assistant sees the same contacts, pipelines, and reports you do.
Safety model
Every call is scoped to one business and one user role; an external assistant can never see or touch another business.
Destructive and real-money actions (deleting records, bulk email sends, publishing sites, launching ad spend) are blocked over MCP. Assistants can draft them; a human confirms them in the Plyto app.
Every MCP tool call is written to the business audit log with the key that made it. Revoke any key instantly in Settings → API keys.
Protocol details
Streamable HTTP (JSON-RPC over POST) at https://plyto.ai/api/mcp. Protocol versions 2024-11-05 through 2025-06-18. Capabilities: tools. Auth: Authorization: Bearer plyto_at_…. The server is reachable from the public internet, including Anthropic's infrastructure for claude.ai connectors.