Skip to main content
Glama
rilfi

token-optimizer-jev-mcp

by rilfi

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
JEV_API_KEYNoFallback if TYPESAFE_API_KEY is unset.
JEV_TIMEOUT_MSNoTimeout per attempt, in milliseconds.30000
TYPESAFE_API_KEYNoTypeSafe API key. Read by this server and by the SDK.
TYPESAFE_BASE_URLNoAPI root (for a proxy).https://api.typesafe.ai
JEV_MAX_INPUT_TOKENSNoEstimated request budget before a local refusal.60000
JEV_MAX_STATE_TOKENSNoEstimated state budget before a local refusal.30000
JEV_BUDGET_WARN_RATIONoFraction of the budget past which a response carries a warning.0.8
TYPESAFE_DEFAULT_MODELNoModel used when a call omits model.jev-latest
JEV_CONFIDENCE_THRESHOLDNoBelow this, answers are flagged needs_review / uncertain.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

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
jev_askA

Ask Jev one or more typed questions about a state and get calibrated decisions back. Mixed question types share one request: every question is evaluated against the state in parallel, so extra questions cost a few tokens and almost no latency. Prefer one call with many questions over many calls. Jev decides, it does not generate: every question needs a defined answer space (a label set, a rubric, yes/no), and it cannot summarize, translate, write code or explain its reasoning. Read-only: the request has no side effects.

jev_choiceA

Ask Jev to pick exactly one label from a defined set. Returns the selected label, the calibrated confidence in it, and — when asked — the probability of every label. Use it for routing, classification, and screening. Read-only: the request has no side effects.

jev_scoreA

Ask Jev to rate a state against an ordered rubric. Returns the expected score (which may fall between levels), its confidence, and — when asked — the probability of each level. Split a judgment that depends on several factors into one score per factor and combine them in your own code. Read-only: the request has no side effects.

jev_noulA

Ask Jev a yes/no question and get back P(yes) as a calibrated probability. There is no separate confidence for a noul answer — the probability is the answer, so treat values near 0.5 as unresolved. Read-only: the request has no side effects.

jev_list_modelsA

List the model names this account can send in a model field, with a description and release date each, plus what the aliases jev-latest and jev-preview currently point to. The versioned ID that answered a request is reported in that answer's model field.

jev_server_infoA

Report this server's configuration and safety limits: base URL, default model, whether an API key is present (never the key), the context budget and how an over-budget request is refused, the confidence threshold, how other MCP clients connect, and the tool list. Use it to confirm what an agent is actually connected to.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.1/5.0

Scored across 6 tools

Disambiguation3/5

jev_ask can handle label sets, rubrics, and yes/no questions, so it overlaps with jev_choice, jev_score, and jev_noul for single-question use. The specialized tools are individually clear, but an agent could reasonably hesitate between the generic ask tool and the specialized one.

Naming Consistency4/5

All tools share a consistent jev_ prefix and lowercase snake_case style, with list_models and server_info following a recognizable pattern. The names score, ask, choice are concise, though jev_noul is cryptic and not clearly verb- or noun-shaped.

Tool Count5/5

Six tools is well-scoped for a decision-serving MCP: four distinct question modes plus two informational endpoints. Each tool earns its place, and the count is comfortably inside the expected range.

Completeness5/5

The surface covers all stated capabilities: rubric scoring, label choice, yes/no probability, mixed parallel questions, model metadata, and server configuration. The explicit design limitation that Jev does not generate text explains why generation/rewrite tools are absent, leaving no obvious dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues