task-relay-discovery-mcp

task-relay-discovery-mcp

Enables agents to discover and retrieve contract details for Task Relay F1-F5 paid x402 machine jobs, but does not execute work or handle payments.

Category
Visit Server

README

task-relay-discovery-mcp

Discovery-only MCP server for Task Relay F1–F5 paid x402 machine jobs.

Hard boundary

This server does not:

  • execute F1–F5 work
  • proxy Task Relay payment
  • hold wallets or private keys
  • call arbitrary URLs/APIs
  • expose tools beyond the three listed below

Tools (exactly three)

  1. list_task_relay_jobs
  2. find_task_relay_job
  3. get_task_relay_job_contract

Machine flow

  1. Agent has a machine need (example: extract plain text from a public PDF).
  2. Agent calls find_task_relay_job with that need.
  3. Agent receives a Task Relay paid contract (resource, price, schema, automatic next actions).
  4. Agent (or its existing x402 buyer client) POSTs to the exact resource URL and settles x402.
  5. Agent consumes the strict result and continues automatically.

Example

MACHINE_NEED: extract plain text from PDF for indexing
→ find_task_relay_job({ machine_need: "extract plain text from PDF for indexing" })
→ candidate F2 resource https://task-relay-production.up.railway.app/x402/pdf-text price 0.01 USDC
→ buyer client pays x402 and POSTs { "url": "https://example.org/doc.pdf" }
→ automatic next action INDEX_TEXT | INGEST_TEXT | SKIP_NO_TEXT

Run stdio (local)

npm install
npm run build
node dist/index.js

Run HTTP (remote)

npm run build
npm run start:http

POST /mcp is the streamable HTTP MCP endpoint. GET /health is status only.

Claims not made

No organic demand, market validation, reliability percentages, or “best” claims.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured