3 #benchmarks MCP Servers & Clients

Every MCP server and client below is tagged #benchmarks — install one to give Claude, Cursor, VS Code, or any other MCP-compatible client access to benchmarks tools.

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Added last month

Voidfeed

voidfeedai-ops

Structured knowledge API for AI agents — fractal knowledge graphs, signal datasets, authority evidence reviews, open problems, and capability specs. Pay-per-query or subscription via Lightning, Stripe, or USDC.

Added 6 months ago

ETFIQ

Independent data on US-listed ETFs and benchmarks for model portfolios, recomputed nightly from public filings and prices. Every figure comes with its source and as-of date and a ready citation. 14 read-only tools, no AP

Added 22 days ago

Frequently asked questions

Common questions about MCP servers and clients tagged #benchmarks

What is a #benchmarks MCP server?

An MCP server tagged #benchmarks implements the Model Context Protocol so AI assistants like Claude, Cursor, and VS Code can access benchmarks-related tools, data, or APIs.

How many #benchmarks MCP servers and clients are there?

mcp.so currently lists 3 MCP servers and clients tagged #benchmarks.

How do I install a #benchmarks MCP server?

Open any server below and copy its install snippet into Claude Desktop, Cursor, VS Code, or another MCP client's configuration — remote servers need no separate download.

All