Documentation
Ask for data in plain language
Connect FastFetchz to Claude and ask for social and web data the way you'd ask a colleague — no API key, no code. "Get the Instagram profile for @nasa" is a complete instruction. Claude picks the right service, runs it against your account and hands back the result.
The connection is authorised in your browser with OAuth, so there is no key to paste and no key to leak. You approve it once on a FastFetchz consent screen, it uses your existing credit balance, and you can revoke it whenever you like. Everything below works the same for a developer wiring this into Claude Code and for a buyer who just wants answers in a chat window.
Connector URL
https://fastfetchz.com/mcp
This is the only value you ever need to paste. Anything that asks for an API key is not this connector.
Connect Claude (web)
- 1Go to claude.ai/customize/connectors
- 2Click +, then Add custom connector
- 3Paste https://fastfetchz.com/mcp
- 4Click Add, then Connect, and approve on the FastFetchz consent screen
Team and Enterprise plans: an organisation owner adds it under Organization settings → Connectors → Add → Custom. After that, each member connects it from their own connectors page and authorises their own FastFetchz account.
Connect Claude desktop
Claude desktop uses the same Connectors UI as the web app — open Settings → Connectors, or use the + next to the prompt box, and follow the same four steps above.
Do not edit claude_desktop_config.json for this. Remote OAuth servers like FastFetchz are added through the Connectors UI. That config file is for local stdio servers, and adding FastFetchz there will not work.
Connect Claude Code
claude mcp add --transport http fastfetchz https://fastfetchz.com/mcpThen, inside a session, run /mcp, select fastfetchz, choose Authenticate, and approve in the browser window that opens.
claude mcp list
claude mcp get fastfetchzThose two commands show whether the server is connected and what URL it points at.
Default. Available in the current project only.
Written to .mcp.json in the repo, so everyone working on it gets the server.
Available across all of your projects on this machine.
Connect Cursor
Add the server to .cursor/mcp.json in the repo, or ~/.cursor/mcp.json to make it global:
{ "mcpServers": { "fastfetchz": { "url": "https://fastfetchz.com/mcp" } } }Caveat: this reflects Cursor's documented behaviour as described by third-party sources rather than something we have verified ourselves. If it doesn't work, check Cursor's own MCP documentation — treat the Claude instructions above as the tested path.
The five tools
Only fetch costs anything. The other four exist so an assistant can look before it leaps — discover what's available, check the target format, and price the job before spending a single credit.
Lists the 24 platforms in the catalog.
Every service, what to pass as the target, and what comes back.
Calls, credits and dollars for a job before you run it.
Runs a data request and returns normalized JSON.
Your credit balance and account status.
What it feels like
Prompts a customer can paste as-is once the connector is live:
- “What FastFetchz services are available for TikTok?”
- “How much would it cost to get 50,000 followers of @nike on X?”
- “Get the Instagram profile for @nasa”
- “Pull the last 20 tweets from @elonmusk and summarise the themes”
- “What's my FastFetchz credit balance?”
- “List every YouTube service and tell me which one needs a video ID”
Before and after
You ask: “How much would it cost to get 50,000 followers of @nike on X?”
Claude does: calls estimate_cost for the X followers service, reports that 50,000 followers is roughly 250 calls at 3 credits each — about 750 credits — and then stops and asks whether you want it to run. Nothing is charged until you say yes.
Credits, honestly
- Same meter as the API. fetch spends the same credits as the REST API — same prices, same balance, one account.
- Every response reports the cost. Each fetch returns credits charged and credits remaining, so the assistant can tell you where you stand without you asking.
- Visible in your dashboard. MCP calls show up in usage and logs alongside API calls, tagged as MCP.
- Running out is explicit. A short balance returns an error naming the shortfall, with a link to top up — it never partially runs a job.
- Rate limits follow your credit pack, exactly as they do on the API.
- Failed calls are never charged.
Want to price a job yourself first? Use the calculator.
Sandbox responses
Some catalog endpoints do not yet have a connected data source. Those return clearly-labelled sample data and cost nothing. The response begins with a warning telling the assistant that the payload is sample data and must not be presented as real.
That warning is a safety feature, not a footnote. An assistant that quietly summarised invented follower counts as fact would be far worse than an error, so we make the shape of the response available for building against while making it impossible to mistake for live data.
Troubleshooting
New tools don't appear
The most common issue by far — clients cache the tool list. In Claude Code, run /mcp and choose Reconnect. In Claude web or desktop, disconnect the connector and add it again. Nothing is lost by reconnecting.
Asked to sign in again
The connection refreshes itself in the background. If it fully expires, reconnect once and you're done.
"Insufficient credits"
Your balance is below the cost of the job. Top up and rerun the prompt.
Wrong or empty results
Check the target format for that specific service with list_services. A username and a post URL are not interchangeable, and some services want an ID rather than a handle.
Pack prices and rate limits live on the pricing calculator.