MCP-Gatekeeper
by sudo-hrmn
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | Yes | Model name to use for the LLM security classifier. | |
| FAIL_CLOSED | No | If 'true', any classifier failure, timeout, or unhandled exception blocks the payload. | true |
| LLM_API_KEY | Yes | API key for the LLM security classifier (supports Groq, OpenAI, DeepSeek, Ollama). | |
| LLM_API_URL | Yes | URL of the OpenAI-compatible LLM API endpoint used by the Stage 2 semantic classifier. | |
| DATABASE_URL | Yes | SQLAlchemy database URL for audit trail and policy storage. | |
| ADMIN_API_KEY | Yes | Secret key required for admin dashboard access and approval of held high-risk actions. | |
| CLASSIFIER_TIMEOUT_SECONDS | No | Timeout in seconds for the LLM classifier call. | 10.0 |
| CONFIRMATION_TIMEOUT_SECONDS | No | Timeout in seconds for human approval of held high-risk actions. | 60 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues