> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentkey.app/llms.txt
> Use this file to discover all available pages before exploring further.

# LinkedIn data for AI agents

> LinkedIn profiles and member activity, post and article detail, comments, company pages and posts, job search and job detail through AgentKey — no partner API.

LinkedIn is the record of who works where and what professionals are saying,
and it is one of the most closed platforms on the web: the official API is
limited to approved partners and the site aggressively blocks anonymous
visitors. Through AgentKey your agent reads public LinkedIn data the same way it
reads everything else — `find_tools`, `describe_tool`, `execute_tool` — with
more than one provider behind the scenes, so one route failing does not stop
the task.

## What you can ask

* *"Summarize what this person has posted on LinkedIn in the last month."*
* *"Get the headline, location and current role from this LinkedIn profile."*
* *"Pull the comments on this post and tell me which companies the commenters work for."*
* *"What has Anthropic's company page published recently?"*
* *"Find open machine-learning engineer jobs in Berlin on LinkedIn."*
* *"Give me the full description of this job posting."*
* *"Which posts has this founder commented on or reacted to lately?"*
* *"Compare the posting cadence of these three company pages this quarter."*

## What's covered

**People**

* Profile by username or by profile URL — name, headline and the other core
  profile fields
* A member's activity, filtered by type: the posts they published, the posts
  they commented on, the posts they reacted to
* Offset and continuation-token pagination, so a long history can be walked
  page by page

**Posts**

* Detail for a post or a long-form article
* Comments sorted by relevance or by most recent, page by page, optionally
  narrowed to one share of the post

**Companies**

* Company profile — the public page's description and details
* The posts published on a company page

**Jobs**

* Job search
* Job detail for a single posting, as shown on the job page

A typical task chains these: resolve the person from a profile URL, pull their
activity, then fetch the comments on the posts that matter — or search jobs,
then open the detail of each shortlisted posting.

## How to use it

Pass the request in plain language and let the router pick the tool:

```text theme={null}
find_tools(q="what this person has posted on LinkedIn in the last month")
find_tools(prefix="social/linkedin")       # browse everything for LinkedIn
describe_tool("<returned Provider/Operation>")
execute_tool("<Provider/Operation>", { ...params })
```

Both English and Chinese phrasing work, and the platform's usual English and Chinese names all land here. Always `describe_tool` before executing — parameters and
per-call costs differ between providers.

> [!NOTE]
>
> **Building with code?** The same capability is available as fixed-contract
> [Scenario Methods](/api-reference/scenario/overview) with automatic provider
> failover:
> [`social.linkedin.post.get`](/api-reference/scenario/methods/social-linkedin-post-get),
> [`social.linkedin.user.get`](/api-reference/scenario/methods/social-linkedin-user-get).
> Member activity, company pages and jobs are available through the catalog
> tools above.

## FAQ

> **Do I need a LinkedIn account or partner API access?**
>
> No. AgentKey holds the upstream access; your agent only needs your AgentKey
> subscription.

> **Can it read connection-only content or send messages?**
>
> No. Only what a profile, company page or post exposes publicly is
> available, and every tool is read-only — no connection requests, messages
> or posting.

> **Is job data current?**
>
> Every call goes to LinkedIn at request time, so job search and job detail
> reflect the listings that are live at that moment.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.