How to connect Ollama to LinkedIn, step by step

What you need

• A Finchreach account (sign in at finchreach.com) and the LinkedIn account you want Ollama to work on.
• An MCP client to run Ollama in: Goose, Claude Code or Codex.
• 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 “Ollama”.
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: Run Ollama in an MCP client and add Finchreach

Ollama doesn’t connect to MCP servers itself, so the client you run it in does. Depends on the client: the client sends the Finchreach key, Ollama only runs the model. The field names for ollmcp and Open WebUI come from their projects, not from Ollama.

1. Pick an MCP client that uses Ollama as its model provider: Goose (Ollama has an official integration page), Claude Code or Codex pointed at Ollama, ollmcp (mcp-client-for-ollama), or Open WebUI (External Tools → MCP Streamable HTTP with a Bearer key).
2. Add Finchreach to that client. For ollmcp, use the config below.
3. Use a model that supports tool calling, such as qwen3 or llama3.1 and later.

{
  "mcpServers": {
    "finchreach": {
      "type": "streamable_http",
      "url": "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 Ollama can read it from an environment variable, prefer that.

Client guides with the exact config:

• Goose (connects, with conditions)
• Claude Code (connects directly)
• Codex (connects directly)

Step 4: Test the connection

In the client you connected, start with a read:

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. The assistant can check the result with linkedin_get_action: pending, approved, rejected, executed, failed or expired.

Troubleshooting

• If the model never calls a tool, it probably doesn’t support tool calling; switch models.
• Small local models can misuse tools; every write still waits for your approval in Finchreach.
• 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 Ollama’s documentation, checked on 2026-10-28; client screens change often.

What to ask it next

Ask your assistant“With a local model, summarize my LinkedIn messages without sending them to a cloud model.”

Ask your assistant“Draft a LinkedIn post from my notes using a local model.”

Ask your assistant“List my new LinkedIn connections from this week and draft a welcome message for each.”

More ideas on the Ollama integration page.

Common questions