{"name":"io.github.RudrenduPaul/agent-eval","slug":"rudrendupaul-agent-eval","title":null,"description":"Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.","url":"https://mcp.market/server/rudrendupaul-agent-eval","rating":null,"grade":"A","score":85,"certified":false,"status":"active","category":"devtools","tags":["devtools","ai"],"presence":{"score":24,"stars":0,"forks":0,"downloads_week":59,"last_push_at":"2026-09-18T17:40:08.000Z","license":"Apache-2.0"},"uptime":null,"claimed":false,"transport":"pypi","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/RudrenduPaul/agent-eval","website":null,"version":"0.1.8","remotes":[],"packages":[{"registryType":"pypi","identifier":"agent-regress-cli","version":"0.1.8","runtimeHint":"uvx","transport":{"type":"stdio"},"runtimeArguments":[{"value":"agent-regress-cli","type":"named","name":"--from"}],"packageArguments":[{"value":"agent-regress-mcp","type":"positional","valueHint":"script_name"}]}],"tools":[{"name":"run","description":"","write_action":true,"price_micros":0,"input_schema":null}],"scan":{"score":85,"grade":"A","scanned_at":"2026-09-23T21:39:09.048Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-23T21:39:09.072Z","components":{"code":{"score":20,"max":25,"notes":["26 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 5 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[{"id":"exec.shell-true","severity":"medium","component":"code","title":"subprocess with shell=True","evidence":"agent_regress_cli-0.1.8/src/agent_regress/core/runner.py: ….run( # noqa: S603 -- fixed argv list, shell=True never used [python_executab…"}],"inputs":{"packages":[{"registryType":"pypi","identifier":"agent-regress-cli","version":"0.1.8","found":true,"weeklyDownloads":59,"license":"Apache-2.0","dependencyCount":14,"publishedAt":"2026-08-10T20:22:07.433246Z","repositoryUrl":"https://github.com/RudrenduPaul/agent-eval"}],"repo":{"found":true,"owner":"RudrenduPaul","repo":"agent-eval","archived":false,"pushedAt":"2026-09-18T17:40:08Z","stars":0,"forks":0,"openIssues":8,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/38769913?v=4","ownerCreatedAt":"2018-04-26T21:59:35Z","license":"Apache-2.0"},"icon":{"url":"https://avatars.githubusercontent.com/u/38769913?v=4&s=128","source":"github"},"presence":{"stars":0,"forks":0,"downloadsWeek":59,"license":"Apache-2.0","lastPushAt":"2026-09-18T17:40:08.000Z","score":24}}}},"grade_history":[],"reviews":[]}