# LinkedIn for AI agents. Managed auth, ready-made tools.

> Share posts and read profile details on LinkedIn on behalf of each of your users, where the relevant API permissions are available.

- Page: https://www.agent200.com/tools/linkedin/
- Category: CRM and sales
- Authentication: Managed OAuth
- Identifier in code: `linkedin`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-15

## Instructions for AI agents

Connector: LinkedIn, through Agent200. In code: "linkedin".
What it does: Share posts and read profile details on LinkedIn on behalf of each of your users, where the relevant API permissions are available.
Page: https://www.agent200.com/tools/linkedin/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on LinkedIn's own page, through the authorization link Agent200 returns. Never ask a user for a LinkedIn password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: linkedin_get_profile. Write tools: linkedin_create_post, linkedin_upload_image, linkedin_create_comment, linkedin_delete_post, linkedin_create_page_post. Name "linkedin" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/tools/linkedin/framework/claude/
   https://www.agent200.com/tools/linkedin/framework/chatgpt/
   https://www.agent200.com/tools/linkedin/framework/claude-code/
   https://www.agent200.com/tools/linkedin/framework/muse/
   https://www.agent200.com/tools/linkedin/framework/grok-bot/
   https://www.agent200.com/tools/linkedin/framework/openai-dots/
   https://www.agent200.com/tools/linkedin/framework/claude-duet/
   https://www.agent200.com/tools/linkedin/framework/hermes-agent/
   https://www.agent200.com/tools/linkedin/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the LinkedIn connector, your agent uses supported LinkedIn functionality where the relevant API permissions are available: it reads the signed-in member's basic profile, publishes posts on their behalf and comments on posts. Each user connects their own LinkedIn account through managed OAuth, and your agent stays within the permissions they granted and the operations your project allows.

LinkedIn is the professional network where people and companies share updates, jobs and news.

## LinkedIn tools

- **Get the profile** (`linkedin_get_profile`, read): Read the signed-in member's name, photo and email address.
- **Create a post** (`linkedin_create_post`, write): Publish a text, link or image post as the member.
- **Upload an image** (`linkedin_upload_image`, write): Upload an image to attach to a post.
- **Comment on a post** (`linkedin_create_comment`, write): Add a comment to a post as the member.
- **Delete a post** (`linkedin_delete_post`, write): Remove a post the member published.
- **Post as a page** (`linkedin_create_page_post`, write): Publish a post for a LinkedIn Page the member administers, where page permissions are available.

## Limits you can set

**Turn single tools on or off.** Keep `linkedin_get_profile` on, and switch off `linkedin_create_post` and `linkedin_delete_post` until your agent should publish.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect LinkedIn

Each end user authorizes their own LinkedIn account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own LinkedIn account, once.
const connection = await agent200
  .user("user_123")
  .connect("linkedin");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the LinkedIn tools

Name the user, the model and the tools. The model decides which LinkedIn tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Post this product update to my LinkedIn",
    tools: ["linkedin"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on LinkedIn's own page. You never see or store their LinkedIn password.

**What access is requested.** The permissions shown on LinkedIn's consent screen, such as the member's basic profile and email, and posting on their behalf. Posting for a page also needs the member to be an admin of that page.

## Example requests

- "Post this product update to my LinkedIn"
- "Share our new blog post on LinkedIn with a short intro"
- "Publish a post welcoming our new hire, with this photo"
- "Post the launch announcement on our company page"

## Guides: LinkedIn with your AI framework

- [LinkedIn + Claude](https://www.agent200.com/tools/linkedin/framework/claude.md): Connect LinkedIn to Claude through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [LinkedIn + ChatGPT](https://www.agent200.com/tools/linkedin/framework/chatgpt.md): ChatGPT cannot send an API key to a custom MCP server, so this guide builds LinkedIn into your own agent with OpenAI's models and the Agent200 SDK.
- [LinkedIn + Claude Code](https://www.agent200.com/tools/linkedin/framework/claude-code.md): Have Claude Code build a LinkedIn agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.
- [LinkedIn + Muse](https://www.agent200.com/tools/linkedin/framework/muse.md): Connect LinkedIn to Muse through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [LinkedIn + Grok Bot](https://www.agent200.com/tools/linkedin/framework/grok-bot.md): Connect LinkedIn to Grok Bot through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [LinkedIn + OpenAI Dots](https://www.agent200.com/tools/linkedin/framework/openai-dots.md): Dots cannot send an API key to a custom MCP server, so this guide builds an always-on LinkedIn agent with OpenAI's models and the Agent200 SDK.
- [LinkedIn + Claude Duet](https://www.agent200.com/tools/linkedin/framework/claude-duet.md): Connect LinkedIn to Claude Duet through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [LinkedIn + Hermes Agent](https://www.agent200.com/tools/linkedin/framework/hermes-agent.md): Connect LinkedIn to Hermes Agent through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [LinkedIn + OpenClaw](https://www.agent200.com/tools/linkedin/framework/openclaw.md): Connect LinkedIn to OpenClaw through Agent200's MCP server: managed OAuth, ready-made tools and one API key.

## FAQ

### Who handles the LinkedIn OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for LinkedIn.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's LinkedIn connection, never another user's. It cannot reach anything the user or LinkedIn has not authorized.

### Can I limit what my agent can do in LinkedIn?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [HubSpot](https://www.agent200.com/tools/hubspot.md): Look up and update contacts, companies and deals in your users' HubSpot CRM.
- [Salesforce](https://www.agent200.com/tools/salesforce.md): Query and update accounts, contacts and opportunities in Salesforce.
- [Zendesk](https://www.agent200.com/tools/zendesk.md): Search, read, create and update Zendesk tickets, and reply to customers, on behalf of each of your users.
- [Stripe](https://www.agent200.com/tools/stripe.md): Look up Stripe customers, payments and invoices, and create invoices and payment links, on behalf of each of your users.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
