evalscopebench-mcp — Claude Code MCP server for AI SDK benchmarks
A paid remote MCP endpoint that lets an agent run AI SDK benchmark gates, compare model scores and pull reports with receipts.
claude mcp add --transport http evalscopebench-mcp https://evalscopebench.clauxel.com/mcpWhat evalscopebench-mcp does
Four tools come with the endpoint: run_benchmark_gate, compare_model_scores, read_benchmark_report and issue_benchmark_receipt. An agent calls them to run a gate, line up scores from different models, or fetch a report. Everything returns as structured JSON, and each operation produces a receipt you can keep as workflow evidence.
Nothing runs on your machine. The endpoint sits at https://evalscopebench.clauxel.com/mcp and needs a client that speaks Streamable HTTP. A public server card is published at https://evalscopebench.clauxel.com/.well-known/mcp/server-card.json; the registry name is com.clauxel.evalscopebench/evalscopebench-mcp.
Access is paid. Production calls carry a bearer token issued from the product site, and an unauthenticated hit on /mcp just returns a JSON error. So the order matters: pick a plan, get the token, then wire the endpoint into your client. The repository holds documentation only — the service code stays private.
What it helps with
- run a benchmark gate before shipping an AI SDK build
- compare two models' scores on the same dataset
- pull a benchmark report as structured JSON
- keep a receipt for every benchmark operation
- expose benchmark checks to an agent over MCP
Example prompts for the agent
- Run the benchmark gate on this build with
run_benchmark_gate - Compare model scores on this dataset using
compare_model_scores - Read the latest benchmark report and issue a receipt
How to install evalscopebench-mcp
Platform CLI: remote server
claude mcp add --transport http evalscopebench-mcp https://evalscopebench.clauxel.com/mcpPlatform CLI: remote server
codex mcp add evalscopebench-mcp --url https://evalscopebench.clauxel.com/mcpConfig file
{
"mcpServers": {
"evalscopebench-mcp": {
"url": "https://evalscopebench.clauxel.com/mcp"
}
}
}Config file
{
"servers": {
"evalscopebench-mcp": {
"type": "http",
"url": "https://evalscopebench.clauxel.com/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http evalscopebench-mcp https://evalscopebench.clauxel.com/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about evalscopebench-mcp
How do I install evalscopebench-mcp in Claude Code?
Run claude mcp add --transport http evalscopebench-mcp https://evalscopebench.clauxel.com/mcp. Get a bearer token from the product site first, since production calls need it.
What does evalscopebench-mcp do?
It gives an agent tools to run AI SDK benchmarks, compare model scores, read reports and issue receipts for each operation.
Do I need a token to use it?
Yes. This is a paid hosted service, and production requests go out with an Authorization: Bearer <token> header issued after you choose a plan.
