What can you do with EvalScope Benchmark MCP?

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

Website: https://evalscopebench.clauxel.com/?utm_source=github&utm_medium=directory&utm_campaign=sbl202605r25
MCP endpoint: https://evalscopebench.clauxel.com/mcp
Server card: https://evalscopebench.clauxel.com/.well-known/mcp/server-card.json
Registry name: com.clauxel.evalscopebench/evalscopebench-mcp

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

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

Useful Links

Product page: https://evalscopebench.clauxel.com/?utm_source=github&utm_medium=directory&utm_campaign=sbl202605r25
Pricing: https://evalscopebench.clauxel.com/?utm_source=github&utm_medium=directory&utm_campaign=sbl202605r25#pricing
Server card: https://evalscopebench.clauxel.com/.well-known/mcp/server-card.json
MCP endpoint: https://evalscopebench.clauxel.com/mcp

Status

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

Install

Add EvalScope Benchmark MCP to your client. Pick the one you use.

claude mcp add --transport http evalscope-benchmark-mcp https://evalscopebench.clauxel.com/mcp

codex mcp add evalscope-benchmark-mcp --url https://evalscopebench.clauxel.com/mcp

{
  "mcpServers": {
    "evalscope-benchmark-mcp": {
      "url": "https://evalscopebench.clauxel.com/mcp"
    }
  }
}

Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.

{
  "servers": {
    "evalscope-benchmark-mcp": {
      "type": "http",
      "url": "https://evalscopebench.clauxel.com/mcp"
    }
  }
}

Add to `.vscode/mcp.json` in your workspace.

{
  "mcpServers": {
    "evalscope-benchmark-mcp": {
      "url": "https://evalscopebench.clauxel.com/mcp"
    }
  }
}

Add to `claude_desktop_config.json`, then restart Claude Desktop.

{
  "mcpServers": {
    "evalscope-benchmark-mcp": {
      "serverUrl": "https://evalscopebench.clauxel.com/mcp"
    }
  }
}

Add to `~/.codeium/windsurf/mcp_config.json`.

2 tools

EvalScope Benchmark MCP exposes 2 tools to a connected agent.

run_benchmark_gate: `compare_model_scores`
read_benchmark_report: `issue_benchmark_receipt`

Score

52 / 100

Adequate

Documentation17/25
Maintenance13/25
Trust6/20
Capability4/15
Install experience12/15

Documents what it does and how to connect
Has a resolvable package or endpoint
Exposes at least one tool, prompt or resource
README has substantive content
Includes a code example
Documents its configuration
Mentions credentials or security posture
Last commit 99 days ago
Has a release history
Repository is not archived
No licence detected
Namespace verified in the official MCP registry
Claimed by its owner
Published under an organisation
2 tool(s) documented
Provides prompt templates
Provides resources
6 documented install method(s)
Published to a package registry
Offers a hosted endpoint — no local install

Read the full rubric →

Version history

Versions	Published
1.0.0Latest	May 25, 2026