agent-eval
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| runA | Run the agent-regress CLI with the given arguments and return its --json output, parsed. Real CLI --help output: Run the agent-regress CLI (statistical regression testing for LLM agents). |
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 available, there is no possibility of confusing it with another; its purpose is clearly described.
The tool name 'run' is a simple, direct verb that matches its function. While it lacks a noun modifier, there is no inconsistency to penalize.
The server has a single tool, which feels thin for a general evaluation platform but is appropriate for a focused CLI wrapper. It is borderline but not excessive.
The server's stated purpose is to run the agent-regress CLI, and the single tool fulfills that. However, it lacks auxiliary capabilities like listing available tests or parsing results separately.