Skip to main content
Glama
GlassTape

GlassTape Policy Builder

Official
by GlassTape

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_PROVIDERNoThe LLM provider for server-side natural language processing (e.g., 'anthropic', 'openai')
OPENAI_API_KEYNoYour OpenAI API key for GPT (when LLM_PROVIDER is 'openai')
ANTHROPIC_API_KEYNoYour Anthropic API key for Claude (when LLM_PROVIDER is 'anthropic')

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": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
generate_policyA

Convert natural language guardrails into enterprise-grade Cerbos YAML policies

validate_policyC

Validate policy syntax using cerbos compile

suggest_improvementsC

Analyze policy for security issues and suggest improvements

list_templatesC

List available policy templates

test_policyC

Run cerbos test on policy and test suite

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: generate_policy creates policies, list_templates shows templates, suggest_improvements analyzes policies, test_policy runs tests, and validate_policy checks syntax. The descriptions make it easy to differentiate between creation, listing, analysis, testing, and validation functions.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with snake_case (e.g., generate_policy, list_templates, suggest_improvements). The naming is predictable and readable throughout the set, with no deviations in style or convention.

Tool Count5/5

With 5 tools, the count is well-scoped for a policy builder domain, covering key operations like generation, templating, analysis, testing, and validation. Each tool earns its place without feeling excessive or insufficient for the server's purpose.

Completeness4/5

The tool set provides strong coverage for the policy lifecycle, including creation, validation, testing, and improvement suggestions. A minor gap exists in update or delete operations for policies, but agents can likely work around this by regenerating or modifying policies through other means.

Maintenance

ActivityInactive
ResponsivenessNo issues