{"name":"net.turingcorp.mcp/decider","slug":"turingcorp-decider","title":"TuringCorp","description":"A decision model for the calls that don't have a right answer. The better option, with a reason.","url":"https://mcp.market/server/turingcorp-decider","rating":null,"grade":"A","score":85,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":23,"stars":0,"forks":0,"downloads_week":null,"last_push_at":"2026-10-16T15:13:51.000Z","license":"MIT"},"uptime":{"percent":100,"checks":28,"ok":28,"last_checked_at":"2026-11-04T01:35:43.236Z","last_ok_at":"2026-11-04T01:35:43.236Z","latency_ms":234},"claimed":false,"transport":"remote","callable_via_gateway":true,"default_price_micros":0,"repository":"https://github.com/TuringCorp-net/MCP","website":"https://mcp.turingcorp.net/","version":"1.0.3","remotes":[{"type":"streamable-http","url":"https://mcp.turingcorp.net/mcp","headers":[{"description":"Bearer <Agent Pass>. Obtain a pass at https://agent-pass.turingcorp.net (self-service signup, email verification, then top up). A pass is valid for 7 days and can be re-rolled.","isRequired":true,"value":"Bearer {agent_pass}","isSecret":true,"variables":{"agent_pass":{"description":"Your TuringCorp Agent Pass. Sign up and top up at https://agent-pass.turingcorp.net; if a call is refused as an invalid credential, sign in there again and re-roll the pass.","isRequired":true,"isSecret":true}},"name":"Authorization"}]}],"packages":[],"tools":[{"name":"decide","description":"Use this when you must choose between two concrete options and both are defensible - two plans, two drafts, two diagnoses, two vendors - and you have no objective way to pick. Not for: more than two options; anything an objective rule settles (a spec, a test, a price, a document); factual lookup; paths that must answer in seconds; high-stakes irreversible calls without review. Fill it in: state task neutrally, without leaning toward either side; give one concrete plan per option - never bundle alternatives into a single one (\"go indoors or postpone\"); keep the two sides comparable in length. Returns the decision inline: betterOption (\"option_A\" or \"option_B\"), confidence (e.g. \"76.7%\"), reason and job_id, all in the same tool result. There is nothing to poll and nothing to fetch afterwards. Reserve 180-300 seconds: this is a long call, and the timeout is a client/host setting, not a parameter you pass. If the call is cut off, do NOT call again - a retry is a new paid call. Retrieve it instead with the get_result tool (same job_id): read-only, free, and no credential of your own needed; with no job_id it lists the ids for your credential. A host that declares the io.modelcontextprotocol/tasks extension can use tasks/get instead. The confidence is the point: it is calibrated, not decorative. On both published benchmarks accuracy rises with it - JudgeBench 99.6% in the 90%+ band down to 67.7% below 70%; the harder ContextualJudgeBench 83.3% down to 55.4% - so route on it: act on a high value, review or escalate a low one, instead of trusting a bare pick. Tables, sample sizes and method: https://api.turingcorp.net Judged by an independent panel, not by a model grading its own output. Read it as a reference, not an instruction, a result, or a prediction; set your own threshold, and apply your own review policy for high-stakes or irreversible decisions. Auth: Agent Pass as `Authorization: Bearer <pass>` (issued at https://agent-pass.turingcorp.net, valid 7 days; each decision is a paid call). On invalid_credential, sign in there and re-roll. Errors: a credential problem is rejected before the call - HTTP 401 with WWW-Authenticate; a business failure (e.g. insufficient balance) comes back as a tool result with isError true plus a second JSON block {error, http_status, action_url, message}, where http_status is the upstream status (the tool call itself is HTTP 200).","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"task":{"type":"string","description":"The decision to make, stated neutrally and without a preferred answer."},"optionA":{"type":"string","description":"First candidate and the case for it."},"optionB":{"type":"string","description":"Second candidate and the case for it."}},"required":["task","optionA","optionB"],"$schema":"https://json-schema.org/draft/2020-12/schema"}},{"name":"get_result","description":"Use this to retrieve the result of an earlier TuringCorp tool call by its job_id - for example a call that was cut off by a client timeout, or one whose id you were given. Retrieval is read-only and free: it starts no new work and costs nothing, so it is always safe to retry. With job_id: that call's status, and once it has finished the same payload the call would have returned inline. Without job_id: the ids available to your credential (7 days). If a call was cut off, retrieve it here instead of calling again - a retry is a new paid call. A job that is not yours and a job that does not exist are answered identically, on purpose. If your client declares the io.modelcontextprotocol/tasks extension, tasks/get reaches the same job.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"job_id":{"description":"Identifier returned by an earlier TuringCorp call (also usable at GET /v1/jobs?job_id=<id>). Omit it to list the ids available to your credential.","type":"string"}},"$schema":"https://json-schema.org/draft/2020-12/schema"}}],"scan":{"score":85,"grade":"A","scanned_at":"2026-11-02T15:58:58.458Z","report":{"scannerVersion":"0.1.10","scannedAt":"2026-11-02T15:58:58.379Z","components":{"code":{"score":-1,"max":25,"notes":["remote-only server, no package to scan"]},"reliability":{"score":20,"max":20,"notes":["remote reachable in 529ms"]},"poisoning":{"score":13,"max":15,"notes":["2 tool descriptions checked"]},"auth":{"score":8,"max":15,"notes":["API key sent as a header"]},"maintenance":{"score":15,"max":15,"notes":["last push 17 days ago"]},"identity":{"score":8,"max":10,"notes":["endpoint served from the registry-verified namespace domain"]}},"findings":[{"id":"poison.long-description","severity":"low","component":"poisoning","title":"Unusually long tool description (over 2,000 characters)","evidence":"tool decide: …Use this when you must choose between two concrete options and both are defensible - two plans, two drafts, two diagnoses, two vendors - and you have no objective way to pick. Not for: more than two options; anything an objective rule settles (a spec, a test, a price, a document); factual lookup; paths that must answer in seconds; high-stakes irreversible calls without review. Fill it in: state task neutrally, without leaning toward either side; give one concrete plan per option - never bundle alternatives into a single one (\"go indoors or postpone\"); keep the two sides comparable in length. Returns the decision inline: betterOption (\"option_A\" or \"option_B\"), confidence (e.g. \"76.7%\"), reason and job_id, all in the same tool result. There is nothing to poll and nothing to fetch afterwards. Reserve 180-300 seconds: this is a long call, and the timeout is a client/host setting, not a parameter you pass. If the call is cut off, do NOT call again - a retry is a new paid call. Retrieve it instead with the get_result tool (same job_id): read-only, free, and no credential of your own needed; with no job_id it lists the ids for your credential. A host that declares the io.modelcontextprotocol/tasks extension can use tasks/get instead. The confidence is the point: it is calibrated, not decorative. On both published benchmarks accuracy rises with it - JudgeBench 99.6% in the 90%+ band down to 67.7% below 70%; the harder ContextualJudgeBench 83.3% down to 55.4% - so route on it: act on a high value, review or escalate a low one, instead of trusting a bare pick. Tables, sample sizes and method: https://api.turingcorp.net Judged by an independent panel, not by a model grading its own output. Read it as a reference, not an instruction, a result, or a prediction; set your own threshold, and apply your own review policy for high-stakes or irreversible decisions. Auth: Agent Pass as `Authorization: Bearer <pass>` (issued at https://agent-pass.turingcorp.net, valid 7 days; each decision is a paid call). On invalid_credential, sign in there and re-roll. Errors: a credential problem is rejected before the call - HTTP 401 with WWW-Authenticate; a business failure (e.g. insufficient balance) comes back as a tool result with isError true plus a second JSON block {error, http_status, action_url, message}, where http_status is the upstream status (the tool call itself is HTTP 200).…"}],"inputs":{"probes":[{"url":"https://mcp.turingcorp.net/mcp","reachable":true,"authRequired":false,"latencyMs":529,"serverInfo":{"name":"turingcorp","version":"1.0.0"}}],"packages":[],"repo":{"found":true,"owner":"TuringCorp-net","repo":"MCP","archived":false,"pushedAt":"2026-10-16T15:13:51Z","stars":0,"forks":0,"openIssues":0,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/229416261?v=4","ownerCreatedAt":"2025-08-30T01:32:27Z","license":"MIT"},"icon":{"url":"https://mcp.turingcorp.net/icon.jpg","source":"registry"},"presence":{"stars":0,"forks":0,"downloadsWeek":null,"license":"MIT","lastPushAt":"2026-10-16T15:13:51.000Z","score":23}}}},"grade_history":[],"reviews":[]}