How to connect Kimi Code to LinkedIn, step by step

What you need

• A Finchreach account (sign in at finchreach.com) and the LinkedIn account you want Kimi Code to work on.
• Kimi 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 “Kimi 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 Kimi Code

1. Edit ~/.kimi-code/mcp.json (or .kimi-code/mcp.json in the project) as below, or use /mcp-config in the TUI.
2. With the legacy kimi-cli: kimi mcp add --transport http finchreach https://mcp.finchreach.com/mcp --header "Authorization: Bearer lk_YOUR_KEY".
3. Restart Kimi Code and check that the finchreach tools are listed.

{
  "mcpServers": {
    "finchreach": {
      "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 Kimi Code can read it from an environment variable, prefer that.

Headers are supported, or "bearerTokenEnvVar": "FINCHREACH_API_KEY" in place of headers to read the key from the environment. OAuth (/mcp-config login <name>) isn’t needed.

Step 4: Test the connection

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

Troubleshooting

• Config paths differ between versions of the docs; if the file isn’t picked up, use /mcp-config to see where your version reads it.
• The kimi.com web chat can’t add MCP servers; use Kimi Code.
• 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 Kimi Code’s documentation, checked on 2026-10-28; client screens change often.

What to ask Kimi Code next

Ask your assistant“Read the diff of this release and draft a LinkedIn post for developers.”

Ask your assistant“Search LinkedIn for engineers who posted about Kimi models and summarize their opinions.”

Ask your assistant“Draft replies to my unread LinkedIn messages, short and friendly.”

More ideas on the Kimi Code integration page.

Common questions