mcp-truth-check
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| verify_turnA | Fact-check your own claims about code you changed, BEFORE telling the user a change is done — to catch over-claims (wrong values, routes or functions you said you added/removed, files you said you edited, 'I only changed X' scope claims, renames, and 'tests pass'). HOW TO CALL: extract the concrete factual claims from what you're about to say and pass them in |
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 ambiguity. The tool's purpose is clearly defined as truth-checking claims.
The tool name 'verify_turn' follows a clear verb_noun pattern, consistent with itself.
A single tool is borderline. The server's scope is narrow (fact-checking), but a single tool handling all verification aspects seems reasonable yet thin.
The tool requires pre-recorded command runs for checking 'tests pass', but no tool is provided to record such runs, creating a significant gap in the workflow.