JevGuard MCP Server

Overview Schema Source Related Servers Discussions Admin

jevguard_evaluate

Evaluate an input state against a set of question criteria through a deterministic pipeline that prunes states, injects escape alternatives, calibrates certainty, and caches results.

Instructions

Executes the deterministic JevGuard evaluation pipeline including state pruning, closed-world escape injection, certainty calibration, and 0-token caching.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "state": "<state>",
      "questions": "<questions>"
    },
    "name": "jevguard_evaluate"
  }
}

Input Schema

Name	Required	Description	Default
`model`	No	Target model identifier (default: jev-latest).	jev-latest
`state`	Yes	Input state payload dictionary or structure to evaluate against criteria.
`timeout`	No	HTTP request timeout in seconds (default: 30.0).
`questions`	Yes	Dictionary of question definitions mapping question keys to criteria (noul, score, choice).
`bypass_cache`	No	Bypass deterministic cache lookup.
`auto_inject_escapes`	No	Automatically inject neutral escape alternatives into categorical choices.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv1.0.1Sep 23, 2026

removedInput schema / properties / api_key

Removed value: -{
-  "description": "Optional TypeSafe AI API key (defaults to TYPESAFE_API_KEY environment variable).",
-  "type": "string"
-}

removedInput schema / properties / endpoint

Removed value: -{
-  "default": "https://api.typesafe.ai/v1/systemone",
-  "description": "Upstream API endpoint (default: https://api.typesafe.ai/v1/systemone).",
-  "type": "string"
-}

removedInput schema / properties / mock_answers

Removed value: -{
-  "description": "Optional raw answers dictionary for testing or offline execution.",
-  "type": "object"
-}

changedInput schema / properties / questions / description

Previous value: -"Dictionary or list of question definitions (noul, score, choice)."New value: +"Dictionary of question definitions mapping question keys to criteria (noul, score, choice)."

removedInput schema / properties / questions / oneOf

Removed value: -[
-  {
-    "type": "object"
-  },
-  {
-    "type": "array"
-  }
-]

addedInput schema / properties / questions / type
```
Added value: +"object"
```

changedInput schema / properties / state / description

Previous value: -"Input state payload to evaluate against criteria."New value: +"Input state payload dictionary or structure to evaluate against criteria."

addedInput schema / properties / state / type
```
Added value: +"object"
```

First observedv1.0.0Sep 21, 2026

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden and does add meaningful traits: deterministic execution, closed-world escape injection, certainty calibration, and 0-token caching. However, it does not disclose side effects, mutation risk, required permissions, or output behavior, leaving significant behavioral context unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence that fits a surprising amount of behavioral and scoping information: deterministic pipeline, four internal stages, and caching behavior. There is no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description gives a solid high-level picture and all parameters are schema-documented, but there is no output schema and no description of what the evaluation returns or how results should be interpreted. For a complex six-parameter tool, that is a meaningful gap, yet the core invocation details are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 without needing extensive parameter explanation. The description adds conceptual context that maps pipeline stages to parameters such as bypass_cache and auto_inject_escapes, but it does not explain parameters directly or exceed what the schema already conveys.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('executes') and resource ('JevGuard evaluation pipeline'), then names four concrete pipeline stages. This clearly distinguishes it from sibling sub-tools such as jevguard_prune_state and jevguard_calibrate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'pipeline including state pruning, ... certainty calibration, and 0-token caching' implies this is the aggregate evaluation tool, while siblings are individual stages. It gives clear context for selection, though it stops short of explicitly naming alternatives or stating when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server