Kitchen MCP Server
by horatio8
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port to listen on (default 3000) | |
| TRUST_PROXY | No | Set to 1 when behind a trusted proxy (e.g., Cloud Run) | |
| MCP_GATE_TOKEN | No | Optional shared bearer token to gate access to the MCP endpoint | |
| ALLOWED_ORIGINS | No | CORS allow-list, e.g., https://claude.ai | |
| KITCHEN_API_KEY | No | Kitchen API key for single-tenant deployments (alternative to per-request header) | |
| KITCHEN_WORKSPACE | No | Kitchen workspace subdomain for single-tenant deployments (alternative to per-request header) | |
| KITCHEN_WEBHOOK_SECRETS | No | Comma-separated webhook secrets to enable webhook receiver | |
| HTTP_RATE_LIMIT_PER_MINUTE | No | Per-tenant HTTP rate limit (default 120) | |
| KITCHEN_WEBHOOK_FORWARD_URL | No | URL to forward verified webhook events | |
| KITCHEN_WEBHOOK_FORWARD_TOKEN | No | Optional token sent as X-Forward-Token header when forwarding webhooks |
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
ActivitySlowing
ResponsivenessNo issues