MCP.Market

XFuel MCP server

by XFuel-Lab·io.github.XFuel-Lab/xfuel-mcp·v0.1.1·1 stars
No reviews yet

Submit AI inference to XFuel, pay per task (USDC via x402 or TFUEL), fetch/verify ZK proofs.

B80/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
Growing

1 stars42 downloads/wk

Reviews

Write one

Nobody has reviewed XFuel yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

XFuel tools (8, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_health

    Check the connected XFuel API's health and configuration (fee config, supported chains, message types, demo limits). Useful for discovery/diagnostics. Args: none. Returns JSON: the /health payload (status, server, version, fee_config, chains, message_types, …).

  • get_proof

    Fetch the SP1 ZK settlement proof for a settled task. Args: - task_id (string): the id returned by submit_inference Returns JSON: { task_id, status, proof_outcome, payment_binding, sp1_proof: { proof, publicInputs, nullifier, provingTimeMs }, fee }. The proof attests settlement metadata + a commitment to the output hash (NOT inference correctness). To validate it, use verify_proof(task_id). Fails

  • get_task_status

    Get the current status of an XFuel task, including proof outcome and fee breakdown. Args: - task_id (string): the id returned by submit_inference Returns JSON: { task_id, status, proof_outcome, message_type, chain_id, gross_amount, fee_amount, net_amount, fee_bps, payment_rail, payment_ref, result, sp1_proof, created_at, updated_at }. 'status' reaches a terminal value ('completed' | 'fee_collected

  • list_models

    List the models XFuel can route inference to (OpenAI-compatible GET /v1/models). Call this first to discover valid model ids, then pass one as 'model' to submit_inference or pay_with_usdc. No side effects. Args: none. Returns JSON: { object: 'list', data: [{ id, object: 'model', created, owned_by }] }.

  • pay_with_usdcwrite action
  • quote_task

    Preview per-rail pricing for a task WITHOUT creating it (no side effects). Use this before submit_inference to show the user cost across payment rails. Args: - model_id (string, optional): model id to price (some models have overrides) - amount (string, optional): TFUEL task value in wei (echoed back in the tfuel rail) Returns JSON: { recommended, default_rail, rails: { usdc: { enabled, asset, net

  • submit_inferencewrite action
  • verify_proof

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan12 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How XFuel compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
80/100
higher than 53% of 1,299 Productivity servers
Tools
8
the typical Productivity server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 854 Productivity servers
Downloads a week
42
more than 30% of 427 Productivity servers with a package

What its tools let an agent do: 6 read · 2 change

Install XFuel in Claude Code, Cursor or VS Code

Runs npx -y xfuel-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add xfuel-mcp -- npx -y xfuel-mcp
Add to Cursor

What the publisher says

From the XFuel repository's README, as published. We do not edit it. Read it on GitHub

Chit402

Chit402 is the book. This agent spent Y on this job. You hold hub, model, and amount.

POST /v1/chat/completions returns a signed receipt: hub, model, amount, verifyurl. Cost-plus, quoted, receipted — pay USDC on Base or Solana. GET|POST /v1/agents/:agentid/book is possession-gated last-N collected spend. Signed receipt is table stakes (HMAC); SP1 settlement proof is on demand. The product is the collected row — sidecar + ingest if you already pay a provider; without a collected USDC payment.ref the receipt is client-attested only. Register is fail-closed: a collected HMAC-valid receipt plus an AAWP official or smart-account agentWallet.

To learn more about the protocol design, read the whitepaper. For live endpoints and what is real vs mock today, see runtime state. Full documentation hub: docs/.

Live app: https://chit402.com Public API: https://api.chit402.com

Table of Contents

  • Setup
  • Using the API
  • Agent toolkit
  • Documentation
  • Security

Setup

Prerequisites

Install Node.js 20+ and npm 10+. A Rust toolchain is required if you build CosmWasm, SP1, or zkLLM crates.

Build and test

Clone the repository, install dependencies, compile contracts, and run the test suite:

git clone https://github.com/XFuel-Lab/chit402.git
cd chit402
npm install
npx hardhat compile
npx hardhat test

Agent gateway

The agent-facing API (settlement, payments, proving, receipts) runs from services/gateway:

cd services/gateway
npm install
npm run m2m-server

The gateway listens on http://localhost:3002 by default. Env examples live under services/gateway/. Production layout is documented in runtime state.

Website

cd apps/web
npm install
npm run dev

Try the paid door

No account. No API key. A wallet that can pay the 402 is enough. Register is only to hold the book after a collected receipt.

curl.exe -sS -D - -X POST https://api.chit402.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{}'

Unauthenticated /v1 returns HTTP 402 with payment requirements (USDC on Base or Solana). The receipt prices the next call. Working copy: docs/DESIGNPARTNERONBOARDING.md.

npm install chit402-sdk
npx chit402-mcp

flagship-demo.ts is the paid /task-request path (402 without a payer). Do not start there.

  • TypeScript SDK — packages/sdk
  • MCP server — packages/mcp
  • Agent playbook — packages/agent-skills

Windows note: if you use raw HTTP, call curl.exe — PowerShell’s curl is not real curl.

API reference: M2M API · Chat completions: docs here · Payments: x402 adapter.

Documentation

Security

Responsible disclosure (safe harbour; no cash bounty until the first audit): docs/bug-bounty.md. Reporting policy: SECURITY.md.

Apache-2.0 — see LICENSE.

Nothing above is checked by us. What we check is on the safety report.

XFuel: common questions

Is XFuel MCP server safe?
Mostly: it is graded B (80/100). Read the XFuel safety report
How do I install XFuel?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does XFuel need an API key?
Yes. The registry entry asks for XFUEL_API_KEY, XFUEL_MCP_AUTH_TOKEN, XFUEL_PAYER_PRIVATE_KEY.
Is XFuel maintained?
The last commit was 39 days ago (2026-09-25). The latest release is v0.1.1.
What can I use instead of XFuel?
Servers from other publishers that do the same job: Research Hub MCP server and devcoach MCP server.
How does XFuel compare with other Productivity MCP servers?
safety score 80/100 (higher than 53% of 1,299 Productivity servers); tools 8 (the typical Productivity server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to XFuel

Same job from other publishers: the closest match first, then the best rated.

  • Research Hub
    Research workspace for Zotero + Obsidian + NotebookLM. Search, ingest, sync, verify briefs.
    A
  • devcoach
    Progressive in-context technical coaching in your AI agent — one local, free lesson per task.
    A