mcpField
X
XFuel

XFuel

Local
github.comAI & Agents1Updated today

About XFuel

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

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"xfuel-lab-xfuel": {
"command": "npx",
"args": [
"-y",
"xfuel-mcp"
],
"env": {
"XFUEL_API_URL": "<XFUEL_API_URL>",
"XFUEL_API_KEY": "<XFUEL_API_KEY>",
"XFUEL_MCP_AUTH_TOKEN": "<XFUEL_MCP_AUTH_TOKEN>",
"XFUEL_RPC_URL": "<XFUEL_RPC_URL>",
"ZK_VERIFIER_ADDRESS": "<ZK_VERIFIER_ADDRESS>",
"XFUEL_PAYER_PRIVATE_KEY": "<XFUEL_PAYER_PRIVATE_KEY>"
}
}
}
}
Run commandnpx -y xfuel-mcp
Environment variables to set
XFUEL_API_URLXFuel API base URL. Defaults to the hosted testnet demo.
XFUEL_API_KEYSecretAPI key sent as X-API-Key. Defaults to the shared public demo key.
XFUEL_MCP_AUTH_TOKENSecretOptional bearer token required on the HTTP transport (Authorization: Bearer <token>).
XFUEL_RPC_URLTheta RPC URL enabling verify_proof's optional on-chain nullifier read.
ZK_VERIFIER_ADDRESSZKVerifierSP1 contract address (paired with XFUEL_RPC_URL).
XFUEL_PAYER_PRIVATE_KEYSecretFunded payer private key that enables the pay_with_usdc tool. Moves USDC — keep secret; use a low-balance wallet.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmxfuel-mcp0.1.1

Tools

8

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
memostringNoFree-form note
modelstringYesModel id, e.g. "llama-3-70b"
amountstringYesGross task value in smallest unit (wei); min 10000
senderstringYes0x address that owns/pays for the task
chain_idenumNoSettlement network (default theta)theta | bittensor | akash | osmosis | persistence
subnet_idintegerNoBittensor subnet id
input_hashstringNokeccak256 of your input
callback_urlstringNoWebhook for signed TaskSettled event
max_gpu_hoursstringNoCompute budget hint

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.