Loading ToolBench
A framework for evaluating agents and MCP servers through automated test suites. Provides a protocol-agnostic core that can evaluate any agent or tool-exposing server by wrapping it in an adapter.
Scoring was not performed
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 19 | 2026-07-28+ | v2 |