MCPGuard
by fridayyy3000
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_PROVIDER_URL | No | URL of the LLM provider for the streaming PII guardrail (Task 3). Defaults to the mock provider. | |
| PRIMARY_MODEL_URL | No | URL of the primary model provider for the rate limiter and fallback router (Task 4). | |
| RATE_LIMIT_DB_PATH | No | Path to the on-disk SQLite database for rate limit storage. Defaults to ./data/task4-rate-limits.sqlite. | |
| PROVIDER_TIMEOUT_MS | No | Timeout for provider calls in milliseconds (Task 4). | |
| SECONDARY_MODEL_URL | No | URL of the secondary model provider used for fallback (Task 4). | |
| LLM_PROVIDER_API_KEY | No | API key for the LLM provider, if required (Task 3). | |
| RATE_LIMIT_WINDOW_MS | No | Length of the rolling rate-limit window in milliseconds. Defaults to 60000. | |
| PRIMARY_MODEL_API_KEY | No | API key for the primary model provider (Task 4). | |
| TOKEN_LIMIT_PER_MINUTE | No | Per-tenant token limit in a rolling 60-second window. Defaults to 50000. | |
| SECONDARY_MODEL_API_KEY | No | API key for the secondary model provider (Task 4). |
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