# How to connect Qwen Code to LinkedIn, step by step

Source: https://finchreach.com/guides/qwen
Third-party facts checked on 2026-10-28.

Create an API key at finchreach.com/api-keys, connect LinkedIn at finchreach.com/accounts, then add `https://mcp.finchreach.com/mcp` to Qwen Code with the header `Authorization: Bearer lk_…`. Test with a read, and approve the first draft under Approvals.

## What you need

- A Finchreach account (sign in at [finchreach.com](https://finchreach.com/sign-in)) and the LinkedIn account you want Qwen Code to work on.
- Qwen Code.
- About five minutes.

## Step 1: Create a Finchreach API key

1. Sign in at finchreach.com and open [API keys](https://finchreach.com/api-keys).
2. Create a key and name it after the tool, for example “Qwen Code”.
3. Copy it right away: it starts with `lk_` and is shown only once.

## Step 2: Connect your LinkedIn account

1. Open [Accounts](https://finchreach.com/accounts) and click to connect LinkedIn.
2. Follow the steps until the account shows as connected.

Approval mode is on by default: nothing the assistant drafts reaches LinkedIn until you approve it.

## Step 3: Add Finchreach to Qwen Code

1. Run `qwen mcp add --transport http finchreach https://mcp.finchreach.com/mcp --header "Authorization: Bearer lk_YOUR_KEY"`. It writes to `~/.qwen/settings.json` by default; add `-s project` for the project.
2. Or edit `settings.json` as below, with `httpUrl` (Streamable HTTP).
3. Restart Qwen Code and run `/mcp` to check the connection.

Terminal:
```bash
qwen mcp add --transport http finchreach https://mcp.finchreach.com/mcp \
  --header "Authorization: Bearer lk_YOUR_KEY"
```

~/.qwen/settings.json:
```json
{
  "mcpServers": {
    "finchreach": {
      "httpUrl": "https://mcp.finchreach.com/mcp",
      "headers": {
        "Authorization": "Bearer lk_YOUR_KEY"
      }
    }
  }
}
```

> Replace `lk_YOUR_KEY` with your key. Keep the key out of shared files and repos; where Qwen Code can read it from an environment variable, prefer that.

Headers are supported. In settings, `httpUrl` means Streamable HTTP and `url` means SSE: Finchreach needs `httpUrl`.

## Step 4: Test the connection

In Qwen Code, start with a read. It runs right away and proves the key and the account work:

> Ask your assistant: “List my connected LinkedIn accounts, then summarize my five latest notifications.”

You should see calls to `linkedin_list_accounts` and `linkedin_get_notifications`. Then try a write, which goes to your approval queue instead of LinkedIn:

> Ask your assistant: “Draft a short LinkedIn post saying I’m trying a new AI assistant workflow. Submit it for my approval.”

## Step 5: Approve or reject it in Finchreach

1. Open [Approvals](https://finchreach.com/approvals). The draft is there with its exact text and the account it would go out from.
2. Approve it to publish, or reject it (reject the test post if you don’t want it live).
3. Qwen Code can check the result with `linkedin_get_action`: pending, approved, rejected, executed, failed or expired.

## Troubleshooting

- Using `url` instead of `httpUrl` makes Qwen Code try SSE, which fails.
- Qwen Chat users: switch to Qwen Code or another MCP client for LinkedIn.
- 401 or “unauthorized”: the key is wrong, revoked or missing its prefix. Finchreach accepts `Authorization: Bearer lk_…` or `X-API-Key: lk_…`; check for a missing `Bearer `, quotes or a trailing space.
- A tool is missing: the key’s permissions don’t include it. Create a key with the permissions you need under [API keys](https://finchreach.com/api-keys).
- “No LinkedIn account”: connect one under [Accounts](https://finchreach.com/accounts), or reconnect it if its session expired.
- A post or message “didn’t go out”: it is probably still waiting under [Approvals](https://finchreach.com/approvals). Writes run only after you approve them.

Still stuck? Compare your setup with [Qwen Code’s documentation](https://qwenlm.github.io/qwen-code-docs/en/users/features/mcp/), checked on 2026-10-28; client screens change often.

## What to ask Qwen Code next

> Ask your assistant: “Write a LinkedIn post about the performance gains in this pull request.”

> Ask your assistant: “Find LinkedIn posts about Qwen models from this week and list the most discussed ones.”

> Ask your assistant: “Check my notifications for new connections and draft a thank-you note to each one.”

More ideas on the [Qwen Code integration page](https://finchreach.com/integrations/qwen).

## Questions

### I lost my API key. Can I see it again?

No, a key is shown only once. Create a new one under [API keys](https://finchreach.com/api-keys), put it in your config, and revoke the old one.

### Does Qwen Code see my LinkedIn password?

No. Qwen Code only gets your Finchreach API key. Your LinkedIn connection stays in Finchreach, and you can revoke the key at any time without touching LinkedIn.

### Can I use the same key in several tools?

Yes, but one key per tool (for example one named “Qwen Code”) lets you revoke one without breaking the others.

### How do I disconnect Qwen Code?

Revoke its key under [API keys](https://finchreach.com/api-keys); Qwen Code gets a 401 from then on. Then remove the server from its config.

## Sources

- [Qwen Code docs](https://qwenlm.github.io/qwen-code-docs/en/users/features/mcp/)

## Related

- [What Qwen Code can do on LinkedIn](https://finchreach.com/integrations/qwen)
- [Announce your software releases on LinkedIn from Qwen Code](https://finchreach.com/blog/qwen-linkedin-release-announcements)
- [Quickstart and tools](https://finchreach.com/docs)
- [All setup guides](https://finchreach.com/guides)