by rajudandigam · MCP Server · ★ 165
agent-inspect Debug, regression-test, and safely share TypeScript AI-agent behavior—locally. No account · no default upload · metadata-only by default · optional customer-owned Studio AgentInspect turns agent runs into customer-owned evidence: execution trees, deterministic contracts, CI gates, verified-safe bundles, and optional self-hosted review. Website · Docs · npm · GitHub <img src="https://img.shields.io/badge/
| Stars | 165 |
| Forks | 50 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 41.55/100 |
| Open Issues | 20 |
| Last Updated | 2026-10-15 |
| Created | 2026-05-02 |
| Platforms | node |
| Est. Tokens | ~58k |
These tools work well together with agent-inspect for enhanced workflows:
Explore other popular mcp server tools:
agent-inspect is Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.. It is categorized as a MCP Server with 165 GitHub stars.
agent-inspect is primarily written in TypeScript. It covers topics such as ai-agents, ci, cli.
You can find installation instructions and usage details in the agent-inspect GitHub repository at github.com/rajudandigam/agent-inspect. The project has 165 stars and 50 forks, indicating an active community.
agent-inspect is released under the MIT license, making it free to use and modify according to the license terms.