Jev MCP Server

Ask Jev (TypeSafe System One) to pick ONE of 2-100 mutually exclusive options, with calibrated probabilities. The official `choice` question type — for fast, cheap structured decisions: triage, routing, classification, prioritization, tie-breaking among enumerated candidates. Returns probabilities over ALL options (not just the winner), so near-ties are visible. NOT for open-ended generation or multi-step reasoning — use an LLM for those. Args: question: The decision, e.g. "Which error class is most likely the root cause?" options: Mapping of short unique id -> one-line description. 2-100 options. context: Optional background facts that inform the decision. Keep it short. Returns: JSON string: {choice, confidence, probabilities (sorted desc), runner_up, model, latency_ms, usage}

Batch-classify up to 100 items against ONE shared set of categories using Jev. Runs the official `choice` question type once per item and aggregates the results — routing support tickets, labeling log lines, triaging inbox items against your own label set. Much cheaper and faster than an LLM for mechanical labeling. Args: items: 1-100 non-empty strings to classify. options: Mapping of short unique id -> one-line category description. 2-100 options. question: Per-item question; the item itself is appended automatically. context: Optional background facts shared by all items. Returns: JSON string: {results: [{item, choice, confidence, probabilities}], summary (counts per choice, sorted desc), model, total_latency_ms, usage: {input_tokens, output_tokens, calls, cached_calls}}

Ask Jev (TypeSafe System One) which of two candidates — a or b — better satisfies the question. The official `choice` type as a focused A/B judgment: "which error message is clearer?", "which rollout plan fits this service better?", "title A or B?". Returns the preferred side PLUS the probability split, so a 52/48 coin flip is visible instead of hidden. Args: question: What to judge, phrased so one side can win, e.g. "Which error message is clearer?" a: Candidate A text. b: Candidate B text. context: Optional background facts. Keep it short. Returns: JSON string: {preferred: "a"|"b", confidence, probabilities: {a, b}, runner_up, model, latency_ms, usage}

Ask Jev (TypeSafe System One) a yes/no question; returns a 0-1 degree (>= 0.5 leans yes). The official `noul` question type — fast, cheap binary checks: "is this change breaking?", "does this log line match the reported symptom?". No probability list, just the degree. NOT for questions that need multi-step reasoning — use an LLM for those. Args: question: A yes/no question, e.g. "Is renaming a public config key a breaking change?" context: Optional background facts. Keep it short. Returns: JSON string: {noul, verdict, model, latency_ms, usage}

Ask Jev (TypeSafe System One) to grade something on an ORDERED scale of 2-8 levels. The official `score` question type — risk/severity/quality rubrics, e.g. levels ["minor", "moderate", "severe", "critical"]. Returns a fractional 0-based index into `levels` (1.88 = between levels[1] and levels[2], leaning to levels[2]), plus confidence and per-level probabilities. Args: question: What to grade, e.g. "Regression risk of renaming public config key X". levels: 2-8 unique ordered scale points, low to high. context: Optional background facts. Keep it short. Returns: JSON string: {score, nearest_level, confidence, probabilities (sorted desc), model, latency_ms, usage}

One-time onboarding: verify a TypeSafe API key with a live call, then store it locally. Use when TYPESAFE_API_KEY is not set in the server environment: pass your key once (get one at https://console.typesafe.ai/settings/keys). It is verified against the live API, then saved to ~/.config/jev-mcp/key (permissions 0600) and never echoed back. An existing TYPESAFE_API_KEY env var always takes precedence over the stored file. Args: api_key: Your TypeSafe API key (from console.typesafe.ai/settings/keys). Returns: JSON string: {ok, stored_path, verified}

Check ONE claim against supplied evidence; returns a 0-1 support degree (>= 0.5 leans supported). The official `noul` type framed as claim-vs-evidence: fact-check a report line against its source, confirm a log excerpt actually shows the reported symptom, validate a summary against the document it summarizes. Evidence is passed as context — Jev judges only what it is given, never invents evidence. Args: claim: A single falsifiable claim, e.g. "The 404s come from edhub, not the gateway". evidence: The evidence text to check the claim against (log excerpt, doc paragraph, diff). Returns: JSON string: {noul, verdict, model, latency_ms, usage}