EvalScope Benchmark MCP

EvalScope Benchmark MCP là một điểm cuối MCP từ xa có phí dành cho bảng điều khiển điểm chuẩn AI SDK. Nó cung cấp các công cụ JSON có cấu trúc, thẻ máy chủ công khai, quyền truy cập dựa trên mã thông báo, biên nhận sử dụng và kiểm toán.

GitHubDùng thử MCP nàyĐược tài trợ

Tài liệu

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.