warrant-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WARRANT_MCP_POLICY | No | Absolute path to the policy file. If not set, the server looks for .warrant/config.json or .warrant/policy-compiled.json, or fails to start. |
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 |
|---|---|
| check_actionA | Check an intended action against the confirmed policy before performing it. Returns ALLOW or DENY; a DENY cites the governing clause. This tool only checks — it never performs the action, and neither may you when it denies. |
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 possibility of confusion. The tool's purpose is clearly defined as a policy check that returns ALLOW or DENY.
The single tool name 'check_action' follows a clear verb_noun convention and is internally consistent. There are no other names to conflict.
A single tool is too few for a server named 'warrant-mcp' which implies broader policy management. The scope appears severely limited.
The tool only checks actions against an existing policy but provides no tools to view, create, update, or delete policies. This is a significant gap—agents cannot manage the policy store, only query it.