How to connect Roo Code to LinkedIn, step by step

What you need

• A Finchreach account (sign in at finchreach.com) and the LinkedIn account you want Roo Code to work on.
• Roo Code.
• About five minutes.

Step 1: Create a Finchreach API key

1. Sign in at finchreach.com and open API keys.
2. Create a key and name it after the tool, for example “Roo Code”.
3. Copy it right away: it starts with lk_ and is shown only once.

Step 2: Connect your LinkedIn account

1. Open 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 Roo Code

1. Click the MCP icon → Edit Global MCP (mcp_settings.json) or Edit Project MCP (.roo/mcp.json, which wins on conflict).
2. Paste the entry below and save.
3. Check the MCP panel: finchreach should be connected and show its tools.

{
  "mcpServers": {
    "finchreach": {
      "type": "streamable-http",
      "url": "https://mcp.finchreach.com/mcp",
      "headers": {
        "Authorization": "Bearer lk_YOUR_KEY"
      },
      "disabled": false
    }
  }
}

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

Headers are supported. Optional timeout, alwaysAllow and disabledTools fine-tune each server.

Step 4: Test the connection

In Roo 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. 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. Roo Code can check the result with linkedin_get_action: pending, approved, rejected, executed, failed or expired.

Troubleshooting

• Don’t commit .roo/mcp.json with a real key; use the global file for the key.
• Use disabledTools to hide LinkedIn write tools from a mode that shouldn’t draft anything.
• 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.
• “No LinkedIn account”: connect one under Accounts, or reconnect it if its session expired.
• A post or message “didn’t go out”: it is probably still waiting under Approvals. Writes run only after you approve them.

Still stuck? Compare your setup with Roo Code’s documentation, checked on 2026-10-28; client screens change often.

What to ask Roo Code next

Ask your assistant“Draft a LinkedIn post that explains this architecture decision record in plain words.”

Ask your assistant“Read my LinkedIn messages and list the ones asking for a technical answer.”

Ask your assistant“Search LinkedIn posts about Roo Code and summarize what people like and dislike.”

More ideas on the Roo Code integration page.

Common questions