GlassTape Policy Builder
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_PROVIDER | No | The LLM provider for server-side natural language processing (e.g., 'anthropic', 'openai') | |
| OPENAI_API_KEY | No | Your OpenAI API key for GPT (when LLM_PROVIDER is 'openai') | |
| ANTHROPIC_API_KEY | No | Your 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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
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.
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.
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.
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.