MCPMark-Verified

MCPMark-Verified is a benchmark for agentic abilities such as tool use, retrieval and autonomous workflows. The official description says: "A human-verified edition of MCPMark, a benchmark for evaluating MCP tool use across five real server environments — Notion, GitHub, Filesystem, Postgres, and Playwright". Below we describe in simple words what benchmarks of this type generally examine.

MCPMark-Verified measures agentic abilities such as tool use, retrieval and autonomous workflows. In detail, it checks:

• choosing and calling the right tools for a task
• keeping track of what it has already done and what is left
• recovering from failed or contradicting tool results
• completing a defined workflow end-to-end

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: A human-verified edition of MCPMark, a benchmark for evaluating MCP tool use across five real server environments — Notion, GitHub, Filesystem, Postgres, and Playwright. Each task has been re-checked by the benchmark team. Official MCPMark evaluation configuration with a 100-step tool-call budget and 32k max tokens per step. The final result is averaged over 3 runs.

What is the MCPMark-Verified benchmark?

MCPMark-Verified is a benchmark for agentic abilities such as tool use, retrieval and autonomous workflows. The official description says: 'A human-verified edition of MCPMark, a benchmark for evaluating MCP tool use across five real server environments — Notion, GitHub, Filesystem, Postgres, and Playwright'. Below we describe in simple words what benchmarks of this type generally examine.

What does MCPMark-Verified test?

MCPMark-Verified mainly measures agentic abilities such as tool use, retrieval and autonomous workflows. Concretely, it checks: choosing and calling the right tools for a task; keeping track of what it has already done and what is left; recovering from failed or contradicting tool results.

How is the MCPMark-Verified score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get MCPMark-Verified data and scores?

The official source is https://mcpmark.ai/. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/mcpmark-verified/scores) or pull it directly from the Open LLM Radar API with any HTTP client.