{"name":"io.github.Icaro0310/poordjaevin","slug":"icaro0310-poordjaevin","title":null,"description":"Typed answers with calibrated confidence for agents. Local-first, no API key.","url":"https://mcp.market/server/icaro0310-poordjaevin","rating":null,"grade":"A","score":85,"certified":false,"status":"active","category":"other","tags":[],"presence":{"score":34,"stars":6,"forks":0,"downloads_week":146,"last_push_at":"2026-10-13T11:42:37.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"pypi","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/Icaro0310/poordjaevin","website":null,"version":"0.1.1","remotes":[],"packages":[{"registryType":"pypi","identifier":"poordjaevin","version":"0.1.1","transport":{"type":"stdio"},"runtimeArguments":[{"value":"serve","type":"positional"}],"environmentVariables":[{"description":"Backend: 'acp' (Devin's own model), 'local' (offline NLI) or 'auto'","name":"POORDJAEVIN_BACKEND"}]}],"tools":[{"name":"classify","description":"Pick exactly one of `options` for `text` (optional `context`). Returns {choice, distribution, confidence, low_confidence}.","write_action":false,"price_micros":0,"input_schema":null},{"name":"decide","description":"Answer a batch of typed questions in one call. Each item is {\"id\": <name>, \"type\": \"judge\"|\"classify\"|\"rate\", ...that tool's args}. Returns {answers: [{id: <name>, ...that tool's result}]}","write_action":false,"price_micros":0,"input_schema":null},{"name":"djaevin_calibrate","description":"Report: mean confidence on disagreed decisions per tool and a suggested low_confidence threshold. Suggestion only — change POORDJAEVIN_LOW_CONFIDENCE manually if you agree; nothing is applied.","write_action":false,"price_micros":0,"input_schema":null},{"name":"djaevin_usage","description":"Model/quota monitor: decisions and measured ACP turn cost, grouped by model and by tool, read from djaevin_log.db. Observational only — it never changes behavior. A paid model shows up as cost > 0.","write_action":false,"price_micros":0,"input_schema":null},{"name":"gate","description":"Advisory opinion: risk that `action` moves money or destroys data (optional `kind`, e.g. \"money\"|\"data\"). Returns {risk: \"low\"|\"medium\"|\"high\", distribution, confidence, low_confidence, advisory: true, details}. Pure opinion — nothing is blocked, approved or enforced.","write_action":false,"price_micros":0,"input_schema":null},{"name":"judge","description":"Yes/no opinion on `statement` (optional `context`). Returns {answer: \"yes\"|\"no\", p_yes, p_no, confidence, low_confidence}. Advisory: a second opinion to weigh, never a verdict.","write_action":false,"price_micros":0,"input_schema":null},{"name":"keepalive","description":"Renew the model's keep_alive window with one trivial request.","write_action":false,"price_micros":0,"input_schema":null},{"name":"mark_disagreement","description":"Mark a logged decision (its `decision_id`) as wrong. With `correct_choice`, the pair input->correct is promoted to validated few-shot examples. Only mark when the right answer is obvious — disagreement on ambiguous questions has no value.","write_action":false,"price_micros":0,"input_schema":null},{"name":"rate","description":"Rate `text` on `scale`: a short numeric range (\"1-5\") or a list of ordered named levels; `criteria` says what is being rated. Returns {level, score, distribution, confidence, low_confidence}.","write_action":false,"price_micros":0,"input_schema":null},{"name":"usage","description":"Return local inference usage counters for this server process.","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":85,"grade":"A","scanned_at":"2026-10-14T05:24:59.454Z","report":{"scannerVersion":"0.1.10","scannedAt":"2026-10-14T05:24:59.411Z","components":{"code":{"score":20,"max":25,"notes":["33 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 1 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[{"id":"exec.eval","severity":"medium","component":"code","title":"eval / new Function used","evidence":"poordjaevin-0.1.1/src/poordjaevin/backends/local_nli.py: …l.to(self._device) self._model.eval() self._entail_idx = self._find…"}],"inputs":{"packages":[{"registryType":"pypi","identifier":"poordjaevin","version":"0.1.1","found":true,"weeklyDownloads":146,"license":"MIT","dependencyCount":12,"publishedAt":"2026-10-06T13:28:58.761223Z","repositoryUrl":"https://github.com/Icaro0310/devin-judge"}],"repo":{"found":true,"owner":"Icaro0310","repo":"poordjaevin","archived":false,"pushedAt":"2026-10-13T11:42:37Z","stars":6,"forks":0,"openIssues":1,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/188095594?v=4","ownerCreatedAt":"2024-11-11T17:55:20Z","license":"MIT"},"icon":{"url":"https://avatars.githubusercontent.com/u/188095594?v=4&s=128","source":"github"},"presence":{"stars":6,"forks":0,"downloadsWeek":146,"license":"MIT","lastPushAt":"2026-10-13T11:42:37.000Z","score":34}}}},"grade_history":[],"reviews":[]}