taskfuel

Specialist tools for any job — a lead, an image, a song, live data, and more.

CommunityDegradedNo sign-inGlobalFreeRead-only

What it can do

  • Discover: Find a paid endpoint. Keyword search is the fastest path from a task to an endpoint: pass `query`. No results is a real answer — nothing offers that term. Pass `domain` to list one service's
  • Call: Call one of the discovered endpoints and pay for it from the user's balance. Set `dry_run: true` first to read the real price off the endpoint's HTTP-402 challenge without paying — that is the a
  • Balance: The connected account's remaining prepaid balance in USD, and what it has spent so far.

What data it sees

Do you need an account

No: the server works without sign-in

Specialist tools for any job — a lead, an image, a song, live data, and more.

Give your agent a prepaid balance and one connection to hundreds of paid APIs — a lead, an image, a song, live data, and more. No per-tool signups, no API keys, no subscriptions. Your agent discovers an endpoint, pays cents for the call, and gets the result — every call itemized against one balance you cap. TaskFuel handles the payment layer (x402, L402, MPP) behind the scenes, so your agent never holds a card or manages credentials.

Tools

  1. discover — Find an endpoint by keyword, list a service's endpoints, or fetch one endpoint's full docs and schema. Takes an agent from task to callable endpoint in one step.
  2. call — Call an endpoint and pay from the balance. Set dry_run: true to read the exact price before paying, then repeat to execute. No auth headers — TaskFuel handles payment and credentials.
  3. balance — Check remaining balance and total spent.

Spend controls Calls above $10 are refused by default; max_amount_usd tightens the ceiling per call, so a runaway loop hits the wall instead of your balance. Prices come from a real dry-run against the live endpoint, so your agent knows the true cost before it commits. Browse the catalog and price any call for free — you only pay when your agent executes. Every endpoint is tested and priced before listing; dead ones get pulled.

How to connect

How to connect taskfuel to Claude

The server address to paste into Claude settings:

https://taskfuel--taskfuel.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect taskfuel to ChatGPT

The server address to paste into ChatGPT settings:

https://taskfuel--taskfuel.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect taskfuel to Cursor

The server address to paste into Cursor settings:

https://taskfuel--taskfuel.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (3)

Raw names from tools/list. Only developers need these.

discoverFind a paid endpoint. Keyword search is the fastest path from a task to an endpoint: pass `query`. No results is a real answer — nothing offers that term. Pass `domain` to list one service's endpoints, `url` + `method` together for one endpoint's full docs (parameters, request-body schema), or no arguments at all for the allowed service domains.
callCall one of the discovered endpoints and pay for it from the user's balance. Set `dry_run: true` first to read the real price off the endpoint's HTTP-402 challenge without paying — that is the authoritative price for that exact payload, not an estimate (a free endpoint never issues a 402, so its dry run executes and returns the response at $0). Repeat the identical call without `dry_run` to execute it. Calls above $10 are refused; `max_amount_usd` can tighten that ceiling further.
balanceThe connected account's remaining prepaid balance in USD, and what it has spent so far.