Skip to main content

The client won’t add the server

Custom connectors are gated by plan. On claude.ai they need Pro or Max, or a Team or Enterprise workspace where an admin has enabled connectors; on ChatGPT they need Plus, Pro, Business, Enterprise, or Edu. On a managed workspace an admin has to allow custom connectors first, and ChatGPT may also require developer mode.If you can’t get that changed, run the local package in a client that allows local servers, such as Claude Desktop, Claude Code or Cursor.
Leave them blank. Superflow supports dynamic client registration, so your client registers itself when it connects. There are no credentials to copy.
Check the URL is exactly https://mcp.usesuperflow.ai/mcp, including the /mcp path. Some clients silently drop a trailing slash or a missing path and then fail with a generic connection error.

Sign-in fails or keeps looping

Usually a blocked pop-up or a redirect the browser dropped. Allow pop-ups for the client, then start the connection again. If your client opens the sign-in in an embedded browser, try copying the URL into your normal browser.
The consent screen has to be completed, not just the sign-in. If you closed the window on the permissions step, no grant was created. Remove the server from your client and add it again to restart the flow.
A sign-in or key belongs to one workspace. To switch, revoke the connection and reconnect, then pick the right workspace on the consent screen. For a key, switch the workspace at the top of the Superflow app before you create it.

The local package won’t start

Your AI tool shows the server as failed, and its log says “Not signed in”. There is no API key and no saved sign-in. Run npx -y @usesuperflow/mcp login, or set SUPERFLOW_API_KEY.
The key was revoked, expired or mistyped. Create a new one under Settings > Integrations > API keys, or remove SUPERFLOW_API_KEY from your config and run login instead. A key in the config always wins over a sign-in.
Install Node.js 20 or later, then restart your AI tool so it sees the new npx.
Gemini CLI starts MCP servers only in a trusted folder. Trust the folder when it asks, then check gemini mcp list. For a headless gemini -p run, pass --skip-trust or set GEMINI_CLI_TRUST_WORKSPACE=true.

Tools are missing or failing

Restart the client after adding the server. Most clients only read MCP config at startup. Then check the client’s MCP panel (/mcp in Claude Code and the Gemini CLI, Settings → MCP in Cursor) to confirm Superflow is listed and connected.
The key or sign-in lacks the permission that tool needs, and the message names it. Ask the assistant “which account and permissions am I using?” (it calls superflow_get_me), then create a key or connect again with that permission. The tool reference lists what each tool needs.Tools also can’t exceed your own access. If your Superflow account can’t do something, neither can the assistant.
Runs need the Run agents permission and enough AI credits. Ask the assistant to estimate the run first; it shows the cost and your balance.
Runs are asynchronous, and a full-page review takes a couple of minutes. The assistant follows it with superflow_get_run until it completes, so give it time before asking again. A run cannot be cancelled once started.If it fails outright, the usual causes are the same as for any agent run: the page isn’t publicly reachable, the project has no agents enabled, or the workspace is out of AI credits.
The snippet has to be live on the URL the project points at. Check that you published the site after pasting the snippet, that the URL in the project matches the environment you deployed to, and that the page isn’t behind authentication or deployment protection.See the setup guide for your platform, and the CSP rules if your site sets a strict Content Security Policy.
Analytics are computed once a day. When they are not ready yet the tools say so, rather than showing zero activity.

Disconnecting

Removing the server from your client’s config stops it calling Superflow, but doesn’t revoke the access token it already holds. To revoke the grant itself, disconnect Superflow from the client’s connected apps screen, or revoke it in Superflow under Settings > Integrations > API keys, in Connected AI apps. For a package sign-in, run npx -y @usesuperflow/mcp logout. Access dies immediately; anything the assistant already created stays in your workspace.
Still stuck? Reach us from the support section in the dashboard and include the client you’re connecting from.