https://mcp.gtm-api.com/mcp. It exposes 250+ typed tools across 19 toolsets, so Claude, Cursor, ChatGPT or a custom agent runtime can search, connect, message and enrich on a LinkedIn account you own.
MCP and REST are the same contract. Every tool maps 1:1 to an endpoint in the API reference: one Zod schema defines the tool, the endpoint and this documentation, so an agent and your backend code see identical shapes, under the same server-side safety layer. A few account-administration endpoints are REST only, marked x-gtm-surface: api in the OpenAPI documents: API keys, OAuth clients and sessions, parts of billing (checkout, cancel, pause and resume among them), deleting a workspace or transferring its ownership, and retrying or cancelling webhook deliveries. Those stay with you and the app, out of an agent’s reach.
What the tools cover
What to ask
Once a client is connected, the agent picks the tools itself from a plain request. A few that work on day one, each mapping onto the areas above:
Anything that sends (a message, an invitation, a bulk run) goes through the preview and confirm step below; reads run straight away. The wording does not matter, the tools do: every row here is one or two tools from the API reference, chosen by the agent.
Guardrails that matter for agents
- Preview then confirm. Outward actions (sends, bulk dispatches) return a preview and require an explicit confirmation step before anything reaches LinkedIn, so an over-eager agent cannot burn an account on its own.
- Server-side limits. Per-action daily budgets are checked before dispatch, under every tool call. The agent does not need to count; the server refuses when a budget is spent.
- Typed errors. Tools fail with the same 16-code taxonomy as REST, with
recoverableand asuggestionfield written for an LLM to act on.
Where to go
Connect a client
Claude, Cursor, and anything else that speaks MCP.
Search these docs from AI tools
The documentation’s own MCP endpoint.