GTM API: LinkedIn MCP Server

GTM API is a managed LinkedIn MCP server.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • List Toolsets: List the available toolsets (domains) on this server. Each toolset groups related tools (e.g. linkedin.messaging, id.billing). Start here, then get_toolset_tools to inspect one, then ca
  • Get Toolset Tools: List the tools in a toolset. Default (lite) returns name + title + one-line summary; pass verbose:true for full descriptions, safety flags, and parameter names. Run one via call_too
  • Call Tool: Execute any tool by name (discovered via get_toolset_tools) with its arguments object. Behaves exactly like calling the tool on its domain mount. Dangerous tools still require the two-step

What data it sees

Do you need an account

No: the server works without sign-in

GTM API is a managed LinkedIn MCP server. It exposes 160+ typed LinkedIn tools across 10 toolsets over the Model Context Protocol, so an AI agent can run real LinkedIn outreach (send connection requests, message, InMail, enrich, search) on a LinkedIn account you own, wrapped in an anti-detect + rate-limit safety layer. Unlike cookie-scraping open-source servers, it runs on owned accounts with dedicated proxies and server-side limits: self-reported 20,000+ accounts at under 1% monthly ban, MCP + REST + webhooks, from $19/account/mo with unlimited calls.

Docs: gtm-api.com/linkedin-mcp-server Source: github.com/gtm-api/linkedin-mcp

Server tool list (3)

Raw names from tools/list. Only developers need these.

list_toolsetsList the available toolsets (domains) on this server. Each toolset groups related tools (e.g. linkedin.messaging, id.billing). Start here, then get_toolset_tools to inspect one, then call_tool to run a tool.
get_toolset_toolsList the tools in a toolset. Default (lite) returns name + title + one-line summary; pass verbose:true for full descriptions, safety flags, and parameter names. Run one via call_tool.
call_toolExecute any tool by name (discovered via get_toolset_tools) with its arguments object. Behaves exactly like calling the tool on its domain mount. Dangerous tools still require the two-step preview→confirm (pass commit_token inside arguments on the confirm call).