Benchmark measuring an AI agent’s ability to orchestrate multiple tools exposed through Model Context Protocol servers.
- Launched
- Sep 19, 2025
- Models
- —
- Modality
- —
- Open source
- —
- API available
- —
- Releases
- 1
Releases
Sep 19, 2025MCP Atlas releasedBenchmark result
Scale released MCP Atlas to evaluate how well AI agents combine tools across real Model Context Protocol servers.

