jev-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JEV_MODEL | No | Model or alias. Pin jev-1.13.0 if you have tuned thresholds. | jev-latest |
| JEV_TIMEOUT_MS | No | Deadline for one logical call, retries included. | 30000 |
| JEV_MAX_RETRIES | No | Retries after the first attempt, on 429 / 529 / 5xx / network errors. | 3 |
| TYPESAFE_API_KEY | Yes | Bearer token. Missing: the server starts, tools return a clear error. | |
| TYPESAFE_BASE_URL | No | API base. Point at a proxy or a mock. | https://api.typesafe.ai |
| JEV_AUTO_THRESHOLD | No | At or above this certainty, gate is auto. | 0.85 |
| JEV_MAX_CONCURRENCY | No | Parallel requests when jev_rank has to chunk. | 4 |
| JEV_REVIEW_THRESHOLD | No | At or above this (below auto), gate is review; below it, escalate. | 0.6 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jev_evaluateA | Ask Jev — a fast, calibrated judgment model — many typed questions about one shared state; returns probabilities plus a gate computed in code. Use it when no other jev_* tool fits. Writing questions (Jev reads literally):
|
| jev_rankA | Rank files or texts by how well each helps answer a query: a relative Choice over the batch for order, Jev's calibrated yes/no per item for filtering.
Pass |
| jev_pickA | Choose one candidate from a list you already have — grep hits, symbols, failing test names, file paths — instead of guessing. One Choice over the candidate ids plus a |
| jev_verifyA | Check up to 100 claims against one body of evidence: supported / contradicted / not_addressed per claim, with a calibrated confidence.
Pass |
| jev_gate_actionA | Advisory pre-flight check on an action you are about to take: judges whether it is destructive, outward-facing or credential-touching, how far it reaches, and how it relates to what the user asked for — then returns allow / confirm / block from a deterministic policy in code.
NOT A SECURITY BOUNDARY. It is a judgment layer that catches plausible mistakes, and Jev is not hardened against adversarial text: an action or context written to argue for its own approval can shift the result. Never rely on it to contain untrusted input, and never let |
| jev_next_stepA | Decide what an agent should do next after a step: continue / retry / change_approach / ask_user / done, with the reasoning signals behind it.
Use it when a loop has stalled and you are about to guess: a tool returned an error you are unsure how to read, a search came back thin, you have tried the same thing more than once, or you are about to tell the user you are finished.
It is deliberately conservative about |
| jev_list_modelsA | List the model names and aliases this account can send in the |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct judgment primitive: evaluate (generic typed questions), rank (ordered relative ordering over a batch), pick (single choice among known candidates), verify (claim support against evidence), gate_action (safety pre-flight), next_step (loop control), and list_models (enumeration). The main soft spot is jev_evaluate, which is an intentionally broad catch-all that could absorb most of the other use cases; the description mitigates this with an explicit 'use only when no other jev_* tool fits' rule, so overlaps are recoverable rather than confusing.
All seven names share a jev_ prefix and snake_case, and most begin with a clear verb (evaluate, rank, pick, verify, list_models). The deviations are jev_gate_action and jev_next_step, which read as noun phrases rather than verb_noun, but they remain predictable and readable.
Seven tools is a tight, well-scoped set for a judgment/inference backend, each covering a clearly separate decision shape. Nothing looks redundant or padded.
The surface covers the core lifecycle of a judgment layer: ask (evaluate), retrieve and narrow (rank, pick), check claims (verify), guard actions (gate_action), control loops (next_step), and introspect models (list_models). Minor gaps exist — no explicit structured-extraction/classification-over-many-items tool, no cost or budget introspection, and no batch multi-evidence variant of verify — but agents can compose the existing tools to work around these.