# Build a LinkedIn agent with Claude Code

> Have Claude Code build a LinkedIn agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.

- Page: https://www.agent200.com/tools/linkedin/framework/claude-code/
- Connector: [LinkedIn](https://www.agent200.com/tools/linkedin.md)
- Framework: Claude Code
- Updated: 2026-11-15

## Instructions for AI agents

Goal: connect LinkedIn to Claude Code with Agent200.
Guide: https://www.agent200.com/tools/linkedin/framework/claude-code/

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. Make sure LinkedIn is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's LinkedIn account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on LinkedIn.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "linkedin" in the tools. The model decides when a LinkedIn tool is needed; Agent200 executes the call.
7. Check it works with this request: "Post this product update to my LinkedIn"
   What should come back:
   - An answer in `result.output`, built from the user's own LinkedIn data.
   - Behind the scenes, the model calls a LinkedIn tool, such as `linkedin_get_profile`, and Agent200 runs it.
8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in LinkedIn, then retry.

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

## Overview

This guide has Claude Code build a LinkedIn agent with the Agent200 SDK, in your own project. When you finish, your agent can call the LinkedIn tools for each of your users.

Claude Code writes the code from the steps below; Agent200 runs the LinkedIn calls with each user's own connection and handles the OAuth flow and the tokens. You do not build or maintain a LinkedIn integration.

- **Connector:** [LinkedIn](https://www.agent200.com/tools/linkedin/)
- **Works with:** Claude Code · Coding agent, with the SDK
- **Authentication:** Managed OAuth, per end user
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [6 tools](https://www.agent200.com/tools/linkedin/framework/claude-code/#tools)
- **Model in examples:** `openai/gpt-5.6-sol`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) of the dashboard.
- **LinkedIn enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **An end user with a LinkedIn account.** They approve access once, on LinkedIn's own page.
- **Claude Code in your project.** It writes the code with the Agent200 SDK; you review it.

## Connect LinkedIn to Claude Code

### Step 1: Create your Agent200 API key

Open the API keys page in the Agent200 dashboard and choose Create an API key. Copy the key and store it as an environment variable, AGENT200_API_KEY, or in your secrets manager. One key covers LinkedIn and every other connector and model enabled for your project. Keep it out of chats, prompts and source control.

Create an API key: https://agent200.com/platform/apikeys/

File `.env`:

```bash
# Keep the key out of your code, prompts and chats.
export AGENT200_API_KEY="paste-your-key-here"
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Give this guide to Claude Code

Start Claude Code in your project and paste the agent brief from this page, or give it the address of this guide's Markdown version. Claude Code follows the steps below in order: the SDK, the LinkedIn connection and the first request. Review the code it writes before you run it.

### Step 3: Set up the Agent200 SDK

Add the SDK to your project and create a client with the key from the environment.

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 4: Let your user connect LinkedIn

Each end user authorizes their own LinkedIn account once, through managed OAuth. If the user has not connected yet, Agent200 returns an authorization link: show it to them, and they approve access on LinkedIn's own page. Agent200 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 5: Run with the LinkedIn tools

Name the user, the model and LinkedIn in the tools. The model decides when a LinkedIn tool is needed, and Agent200 executes the call with the user's own 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.)

## Test your connection

Ask: "Post this product update to my LinkedIn"

What should come back:

- An answer in `result.output`, built from the user's own LinkedIn data.
- Behind the scenes, the model calls a LinkedIn tool, such as `linkedin_get_profile`, and Agent200 runs it.

If Agent200 returns an authorization link instead, the user has not connected LinkedIn yet. Go back to the connect step.

## LinkedIn tools Claude Code can call

- **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.

## How it works

1. **Your app sends the request.** It calls Agent200 with the model, instructions, the input, the end user's id and the LinkedIn tools.
2. **The model picks a tool.** The model decides whether a LinkedIn tool is needed, and with which arguments.
3. **Agent200 runs the call.** It uses that user's own LinkedIn connection, within the endpoints and scopes your project allows, and returns the result to the model.
4. **Your app gets the result.** Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

**Each user's own connection.** Connections belong to individual end users. A request for one user never reaches another user's LinkedIn account.

**Permissions at every level.** Your project settings decide what the agent may request, the end user decides what they authorize, and LinkedIn enforces what its API grants.

## Troubleshooting

### The request says LinkedIn authorization is required

The end user has not connected LinkedIn yet, or the connection needs to be approved again. Agent200 returns an authorization link: show it to the user, let them approve access on LinkedIn's own page, then run the request again.

### Claude Code does not use the LinkedIn tools

Check that LinkedIn is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming LinkedIn in the request, or in the instructions, also helps the model choose the right tool.

### A tool call is refused or returns less than expected

Agent200 runs only what your project allows (services, endpoints and scopes), and LinkedIn returns only what the end user authorized. Widen the endpoints or scopes in the dashboard if the agent needs more, then ask the user to connect LinkedIn again so they can approve the new access.

### The results come from the wrong account

Every request names an end user (`user_123` in the examples). Pass the id of the person your agent is working for: Agent200 then uses only that user's LinkedIn connection, never another user's.

### The API key was pasted into a chat or committed

Create a new key on the [API keys page](https://agent200.com/platform/apikeys/), update `AGENT200_API_KEY` wherever your app reads it, and stop using the old one. Keep keys in environment variables or a secrets manager, never in prompts, chats or source control.

## Use LinkedIn with another framework

- [LinkedIn + Claude](https://www.agent200.com/tools/linkedin/framework/claude.md)
- [LinkedIn + ChatGPT](https://www.agent200.com/tools/linkedin/framework/chatgpt.md)
- [LinkedIn + Muse](https://www.agent200.com/tools/linkedin/framework/muse.md)
- [LinkedIn + Grok Bot](https://www.agent200.com/tools/linkedin/framework/grok-bot.md)
- [LinkedIn + OpenAI Dots](https://www.agent200.com/tools/linkedin/framework/openai-dots.md)
- [LinkedIn + Claude Duet](https://www.agent200.com/tools/linkedin/framework/claude-duet.md)
- [LinkedIn + Hermes Agent](https://www.agent200.com/tools/linkedin/framework/hermes-agent.md)
- [LinkedIn + OpenClaw](https://www.agent200.com/tools/linkedin/framework/openclaw.md)

---

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