events-mcp
by stkr22
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EVENTS_PORT | No | Port for the MCP server (/mcp, /healthz, /readyz). | 8000 |
| EVENTS_TIMEZONE | No | Timezone used for interpreting bare dates. | Europe/Berlin |
| EVENTS_MCP_TOKEN | No | Static bearer token. If unset, the server runs unauthenticated (development only). | |
| EVENTS_DATABASE_URL | Yes | libpq URL for the Postgres database. | |
| EVENTS_METRICS_PORT | No | Port for Prometheus metrics on its own port. | 9090 |
| EVENTS_EMBEDDING_MODEL | No | Embedding model; must produce 1024-dim vectors. | Qwen3-Embedding-0.6B-8bit |
| EVENTS_EMBEDDING_BASE_URL | No | OpenAI-compatible base URL (…/v1); unset disables semantic search. | |
| EVENTS_EMBEDDING_TIMEOUT_SEC | No | Per-request embedding timeout in seconds. | 5 |
| EVENTS_SEMANTIC_MAX_DISTANCE | No | Cosine distance beyond which a vector hit is dropped. | 0.75 |
| EVENTS_EMBEDDING_QUERY_PREFIX | No | Prefix prepended to search queries only, never to documents. | Qwen3 instruction |
| EVENTS_EMBEDDING_RETRY_AFTER_SEC | No | How long a failed embedding endpoint is skipped before being retried, in seconds. | 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 recent community issues