GATEKEEPER MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pre_action_checkA | Gatekeeper check. Call this BEFORE modifying any code. It verifies whether the change is justified by evidence and whether the task is already solved. If not justified, the agent MUST NOT edit files. Supply an executable reproduction under |
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
The server exposes exactly one tool, `pre_action_check`, so there is no possibility of confusing it with another tool. The purpose of the gate check is single and unambiguous.
The single tool name `pre_action_check` is clear and snake_case, but it does not follow a verb-noun pattern and there is no set of tools to establish a broader naming convention.
With only one tool, the server feels thin for the 'gatekeeper' domain, though the narrow purpose partially justifies the count. Auxiliary tools like policy lookup or reproduction validation are absent.
The core gatekeeping interaction is covered, but the surface lacks related operations such as querying gate rules or validating evidence formats, so coverage is functional but has minor gaps.