get_profile_sections

What it does

The research before a message that does not read like a template: where they worked, what they studied, what they are endorsed for, who recommends them. Skills come with the endorsement id propose_endorsement needs.

Arguments

This table is generated from the literal inputSchema that tools/list returns, so what your client sees and what this page says are the same object:

{
  "type": "object",
  "properties": {
    "profile": {
      "type": "string",
      "description": "Profile URL, public identifier (the /in/ slug) or provider id"
    },
    "sections": {
      "type": "string",
      "description": "Comma-separated: about, experience, education, languages, skills, certifications, volunteering_experience, projects, recommendations_received, recommendations_given. Default: a preview of all."
    },
    "account": {
      "type": "string",
      "description": "Sender account id or name to act as. Defaults to the healthiest connected account."
    }
  },
  "required": [
    "profile"
  ]
}

Request

Paste this, swap the key, and you have called the tool.

curl -s https://topclozer.com/api/mcp \
  -H "Authorization: Bearer tcz_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_profile_sections",
      "arguments": { "profile": "https://www.linkedin.com/in/example", "sections": "experience,skills,recommendations_received" }
    }
  }'

Returns

{ providerId, fullName, headline, summary, location, profileUrl, networkDistance, connectionsCount, followerCount, sharedConnections, flags, invitation, contactInfo, experience[], education[], skills[], languages[], certifications[], projects[], volunteering[], recommendationsReceived[], recommendationsGiven[], throttledSections[] }

The payload arrives inside an MCP content block — one text block whose body is this JSON, pretty-printed. Parse the string; there is no structured-content field.

{ "providerId": "ACoAAB1x…", "fullName": "Dana Whitfield", "headline": "CTO at Northbeam", "networkDistance": "DISTANCE_2", "experience": [{ "title": "CTO", "company": "Northbeam", "start": "3/2023", "end": null, "current": true }], "skills": [{ "name": "Kubernetes", "endorsements": 31, "endorsementId": 9812, "endorsedByMe": false }], "throttledSections": [] }

Worth knowing

Contact info (email, phone) is only visible for first-degree connections. LinkedIn throttles heavy section reads: sections it held back come back empty and are named in throttledSections — ask for fewer sections, later.

Rate limit

30 LinkedIn tool calls per 5 minutes, per workspace. Exceeding it returns HTTP 429 with JSON-RPC error -32002 and a Retry-After header. The budget is shared by every LinkedIn tool and counted per workspace, so minting a second key does not buy a second allowance.

The limit exists because an agent retrying in a loop is the request pattern that gets a LinkedIn account restricted, and a restricted account is a much worse outcome for you than a 429. Workspace tools do not spend this budget.

Related tools

All 65 tools are listed on the tool index. Connecting a client is on the Claude setup page, and the protocol details are on the server page.