Jev Decision MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODEL | Yes | Default model accepted by the configured endpoint. | |
| API_KEY | No | API key for the configured decision endpoint. Required for live decisions; optional for tool discovery. | |
| BASE_URL | Yes | Base URL of a compatible typed-decision API. The SDK appends /v1/systemone. | |
| JEV_TIMEOUT_MS | No | Total request deadline including retries, in milliseconds (1-120000). | 30000 |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jev_decideA | Evaluate supplied context using the configured decision models via the API at https://api.typesafe.ai. Batch independent, narrow questions in one call: choice selects a provided label; score returns a position on 2–10 ordered levels (0-based); noul returns probability of yes, not intensity. Supply relevant evidence and full instructions; question IDs are not sent to the model. Include an other/none choice when appropriate. Questions cannot use each other's answers. Returns raw judgments, probabilities, confidence for choice/score, and token usage. Use caller-defined policies for uncertainty. This sends the supplied state and questions to the Decision API at https://api.typesafe.ai and may incur API charges. It does not execute selected actions. |
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 1 tool
With only one tool, there is no possibility of selecting the wrong tool or confusing overlapping purposes. The single tool's multi-mode parameters are internally coherent.
A single tool name cannot introduce inconsistency across a set. 'jev_decide' is clear and follows a predictable prefix_verb convention.
The server exposes only one tool, which is thin for a general decision-evaluation surface. However, the tool supports multiple decision types and batching, so it is not an extreme mismatch.
The tool covers choice, score, and yes/no probability judgments with batching, which addresses the core decision API. Auxiliary operations like model discovery, configuration, or history are absent but may be outside scope.