Skip to main content
Glama
vengtoo

@vengtoo/mcp-server

by vengtoo

create_policy

Create a policy to allow or deny actions on all resources of a type or on a single resource.

Instructions

Create a policy. A policy grants or denies a set of actions on a resource type (type-level) or a specific resource (instance-level). After creating, assign it to a subject or role with assign_policy.

For type-level: set resource_type_id and actions — the policy applies to ALL resources of that type. For instance-level: set resource_id and actions — the policy applies to ONE specific resource.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesPolicy name, e.g. "editors-can-read-write-documents"
effectYesALLOW grants the actions. DENY blocks them even if another policy would allow. Use ALLOW unless you specifically need an override.
actionsYesActions this policy covers, e.g. ["read", "write"]
priorityNoPriority 0–100. Higher priority wins when multiple policies apply. Default 50.
descriptionNoOptional description
resource_idNoResource UUID — makes this an instance-level policy. Mutually exclusive with resource_type_id.
resource_type_idNoResource type UUID — makes this a type-level policy. Mutually exclusive with resource_id.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, description carries full burden. Discloses that creation is followed by assignment, and explains the two behavior modes. No mention of permissions or reversibility, but creation is straightforward.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short paragraphs with clear separation of purpose and usage instructions. No fluff, every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Lacks return value info (no output schema). Otherwise covers creation process and next steps. Adequate but could mention that the created policy object is returned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all parameters (100% coverage). Description adds context about mutual exclusivity of resource_id and resource_type_id, and explains type vs instance levels, which is not in schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Create a policy' with specific verb and resource. Describes two modes (type-level vs instance-level), distinguishing from sibling tools like assign_policy.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to assign after creation with assign_policy. Explains when to use type-level (set resource_type_id) vs instance-level (set resource_id). Could mention when not to use (e.g., for checking authorization), but adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/vengtoo/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server