Skip to main content

Troubleshooting: MCP

Troubleshooting information for using MoltSets's MCP.

Error: Unknown client_id

If you see an Unknown client_id error when connecting to the MoltSets MCP, one of these is usually the cause:

  1. Incorrect client_id. Double-check the client_id against the value on the API Keys page of the dashboard, then try again.

  2. Not logged into MoltSets first (Team/Enterprise Claude accounts). If you're on a Team or Enterprise plan, you need to log into the MoltSets app before connecting the MCP in Claude. Log in, then retry the connection.

  3. client_id belongs to an account you're not part of. This can happen if the key was copied from a teammate's account or an old workspace. Confirm the client_id was generated from an account you currently belong to. If you do not currently have a MoltSets account but your company does, ask your account owner to invite you to the company MoltSets account.


Connection fails after adding the config

Restart your AI tool after adding the MCP configuration — most clients need a full restart to detect new MCP servers. Verify the URL is exactly https://mcp.moltsets.com/mcp, with no trailing slash and no extra path segments.


The authorization request is rejected (invalid redirect URI)

Terminal clients must call back to a loopback address — 127.0.0.1, localhost, or [::1]. A plain http callback on any other host is refused; everything else must use https.

If your callback is loopback and it is still refused, check that the client sends a PKCE code_challenge (method S256) — it is required for loopback — and that the callback path matches the one registered for your connector. The port is allowed to change between runs; the path is not.


Authentication errors (invalid credentials)

Double-check that your Client ID and Client Secret are copied correctly from app.moltsets.com — no extra spaces, no truncation. If your credentials were recently rotated or revoked, generate a new connector from the API Keys page and update your config, then restart your AI tool.


Network or timeout errors

Check your network connection and try again. If the issue persists, verify the server is reachable by opening https://mcp.moltsets.com/mcp in your browser — if you see any response, even an error page, the server is up and the issue is likely local to your config.


"internal_error" or 500 responses

A 500 with internal_error means the endpoint itself is temporarily offline. Nothing about your call caused it — credentials, parameters, and plan are all fine, and the MoltSets team is alerted automatically, so there's no need to report it. Have your agent stop retrying that tool and come back to it later.


"plan_restricted" on a personal email lookup

linkedin_to_personal_email and linkedin_to_best_personal_email are not available on every plan — access is set per account, not by price tier. Call get_account to check where yours stands. This is an account entitlement, not a data miss, so retrying or rewording the prompt won't help — use linkedin_to_business_email instead.


The agent reports an error when the lookup simply found nothing

Check the status field on the response. A clean miss comes back as a success — isError: false with status: "not_found" — and costs nothing. It is not an error, and retrying the same input will return the same miss. If your agent is relaying misses as failures, have it read status before reporting.

Did this answer your question?