Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

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

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
ackriteA

Classify a technical claim from supplied evidence. Returns support, contradiction, assumptions, missing evidence, and the next action.

verifyB

Separate what is known, assumed, supported, contradicted, and still unverified, then propose a decisive experiment.

auditA

Challenge a proposed code change for scope creep, rewrites, contract assumptions, security implications, error handling, and missing validation.

prove_itA

Define the smallest direct evidence set and experiment required to establish a technical claim without speculation.

reality_checkA

Detect repeated failed strategies, contradictions, unsupported conclusions, untested success claims, and premature rewrites from supplied reasoning and session history.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.3/5.0

Scored across 5 tools

Disambiguation2/5

ackrite, verify, and prove_it all focus on classifying evidence and determining support/contradiction for technical claims, making their boundaries unclear. reality_check also overlaps by detecting contradictions and unsupported conclusions, leaving audit as the only clearly distinct tool.

Naming Consistency2/5

Tool names use a mix of single-word verbs (verify, audit), an underscored phrase (prove_it), a slang term (ackrite), and a compound noun (reality_check). No consistent verb_noun or naming convention is followed.

Tool Count4/5

Five tools is a reasonable number for the server's apparent scope, and none feel truly redundant on count alone. However, the heavy conceptual overlap means a few tools could potentially be consolidated.

Completeness4/5

The set covers claim classification, evidence verification, code change auditing, proof design, and reasoning pattern analysis, which is fairly comprehensive for a technical-decision support domain. Minor gaps like explicit tracking of evolving assumptions exist, but core workflows are covered.

Maintenance

ActivityMaintained
ResponsivenessNo issues