jev-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TYPESAFE_API_KEY | Yes | Required. Your TypeSafe API key from console.typesafe.ai. | |
| TYPESAFE_BASE_URL | No | Override the API host. Useful for staging and tests. |
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 |
|---|---|
| evaluateA | Judge some content against one or more typed questions and get back probabilities rather than prose — a yes/no likelihood (noul), a pick from a named set (choice), or a position on ordered levels (score). Use it wherever you would otherwise ask a model for an answer and then parse the reply. |
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 confusing its purpose with another tool. The tool's description clearly defines its unique role of evaluating content against typed questions and returning structured probabilities.
A single tool named 'evaluate' cannot be inconsistent with anything else, and the name is a clear, verb-based descriptor that matches its function. No pattern mixing or naming conflicts exist to penalize.
The server exposes only one tool for what appears to be a broad evaluation domain. The description suggests a wide range of uses, but one tool provides no supporting workflows, making the server feel too thin for its apparent scope.
The tool covers a single evaluation action, but the broader domain of evaluation likely includes question/template management, batch evaluation, or result history. As it stands, agents can perform isolated evaluations but have no way to manage or reuse evaluation setups, creating dead ends.