search_linkedin_posts — LinkedIn MCP tool reference

What it does

Find who is talking about a problem right now. A comment on that post is a warmer opening than a cold invite.

This tool drives a real LinkedIn account

It runs through a connected sender account in your workspace — not through a scraper and not through your own profile. Call list_sender_accounts first to see which identities are connected and healthy. If the workspace has none, this tool returns an error telling you so; accounts for agents covers how teams get one without risking their own profile.

Arguments

Name	Type	Required	Meaning
keywords	string	yes	Free text
sort_by	string	no	relevance (default) or date
date_posted	string	no	past_day, past_week or past_month
content_type	string	no	videos, images, documents, jobs, live_videos or collaborative_articles
limit	number	no	1–49 (LinkedIn's default is 3)
cursor	string	no	The `cursor` from the previous page, to continue
account	string	no	Sender account id or name to act as. Defaults to the healthiest connected account.

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:

inputSchema

{
  "type": "object",
  "properties": {
    "keywords": {
      "type": "string",
      "description": "Free text"
    },
    "sort_by": {
      "type": "string",
      "description": "relevance (default) or date"
    },
    "date_posted": {
      "type": "string",
      "description": "past_day, past_week or past_month"
    },
    "content_type": {
      "type": "string",
      "description": "videos, images, documents, jobs, live_videos or collaborative_articles"
    },
    "limit": {
      "type": "number",
      "description": "1–49 (LinkedIn's default is 3)"
    },
    "cursor": {
      "type": "string",
      "description": "The `cursor` from the previous page, to continue"
    },
    "account": {
      "type": "string",
      "description": "Sender account id or name to act as. Defaults to the healthiest connected account."
    }
  },
  "required": [
    "keywords"
  ]
}

Request

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

curl

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": "search_linkedin_posts",
      "arguments": { "keywords": "SOC 2 audit", "date_posted": "past_week", "sort_by": "date" }
    }
  }'

Returns

{ searchedAs, count, cursor, posts: [{ id, socialId, url, text, postedAt, author, counts }] }

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.

payload

{ "searchedAs": "Marcus Feld", "count": 1, "cursor": "…", "posts": [{ "id": "7332…", "socialId": "urn:li:activity:7332…", "text": "Our SOC 2 audit took 4 months…", "author": { "name": "Dana Whitfield", "providerId": "ACoAAB1x…" }, "counts": { "reactions": 88, "comments": 21 } }] }

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

get_post

One LinkedIn post: text, author, reactions, comments, reposts, and whether the account can react or comment

list_post_reactions

Who reacted to a LinkedIn post (or one of its comments), with each person's headline and degree — the warmest leads a post produces

propose_comment

Propose a comment on a LinkedIn post, or a reply to a comment on it. NOT posted until approved. Public and permanent.

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.