cyanheads-mcp-server
Officialby cyanheads
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CATALOG_URL | No | Remote fleet.json endpoint (schema v2 with baked embeddings). Must be an absolute URL. Override to front your own fleet. | https://caseyjhand.com/fleet.json |
| OTEL_ENABLED | No | Enable OpenTelemetry | false |
| MCP_AUTH_MODE | No | Authentication: none, jwt, or oauth | none |
| MCP_HTTP_HOST | No | HTTP server bind host | 127.0.0.1 |
| MCP_HTTP_PORT | No | HTTP server port | 3010 |
| MCP_LOG_LEVEL | No | Log level (debug, info, warning, error, etc.) | info |
| SIMILARITY_FLOOR | No | Cosine similarity cutoff for cyanheads_search_catalog results. Must be within [0, 1]. | 0.3 |
| EMBEDDING_MODEL_ID | No | Hugging Face model id for query embedding. Must match fleet.json.embeddingModel. | Snowflake/snowflake-arctic-embed-m-v1.5 |
| MCP_TRANSPORT_TYPE | No | Transport: stdio or http | stdio |
| MCP_HTTP_ENDPOINT_PATH | No | HTTP endpoint path where the MCP server is mounted | /mcp |
| CATALOG_REFRESH_SECONDS | No | Background poll interval for fleet.json refresh. 0 disables; otherwise must be > 0. | 3600 |
| CATALOG_FETCH_TIMEOUT_MS | No | Per-request timeout for fleet.json fetches in ms. Must be > 0. | 10000 |
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
ResponsivenessWithin a week