Search DevTools

Jump to any tool or page

evalscopebench-mcp

A paid remote MCP for AI SDK benchmark dashboard, built to return verdicts, receipts, usage logs, an

clauxel0 stars0 forksDesign & UX
View source

Install

mcp_config.json

{
  "mcpServers": {
    "com-clauxel-evalscopebench-evalscopebench-mcp": {
      "url": "https://evalscopebench.clauxel.com/mcp",
      "type": "streamable-http"
    }
  }
}

Documentation

EvalScope Benchmark MCP

Hosted MCP for AI SDK benchmark dashboard.

EvalScope Benchmark MCP is a paid remote MCP endpoint for AI SDK benchmark dashboard. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-ready workflow evidence for AI agents and coding teams.

Public Endpoints

Access

This is a paid hosted remote MCP. Production calls require a bearer token issued from the product website.

Authorization: Bearer <token>

Unauthenticated browser visits to /mcp return a clear JSON error instead of internal details.

Tools

  • run_benchmark_gate
  • compare_model_scores
  • read_benchmark_report
  • issue_benchmark_receipt

Quick Start

  1. Open the website and choose a plan.
  2. Create or request an API token.
  3. Add the endpoint to an MCP client that supports Streamable HTTP remote servers.
  4. Send JSON-RPC requests with the bearer token.

Useful Links

Status

This repository is a public documentation and directory-submission reference for the hosted service. It does not contain the private production source code.

Sourced from the repository README.

More in Design & UX