Comet ML MCP Server
Officialby comet-ml
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPIK_API_KEY | No | Opik API key. | |
| OTEL_ENABLED | No | Enable/disable telemetry (default: true). | true |
| COMET_API_KEY | Yes | Your Comet ML API key. Required if not using comet init. | |
| OPIK_ENDPOINT | No | Opik endpoint (alternative to OTEL_EXPORTER_OTLP_ENDPOINT). | |
| OPIK_WORKSPACE | No | Comet workspace for Opik. | |
| OTEL_LOGS_FILE | No | Path for log export file (empty to disable). | logs.jsonl |
| COMET_WORKSPACE | No | Optional: Default workspace name. | |
| OTEL_TRACES_FILE | No | Path for trace export file (empty to disable). | traces.jsonl |
| OPIK_PROJECT_NAME | No | Opik project name. | |
| OTEL_SERVICE_NAME | No | Service name for OpenTelemetry (default: comet-mcp). | comet-mcp |
| OTEL_SERVICE_VERSION | No | Service version for OpenTelemetry (default: 1.2.0). | 1.2.0 |
| OTEL_EXPORTER_OTLP_HEADERS | No | Headers for OTLP exporter (comma-separated key=value). | |
| OTEL_EXPORTER_OTLP_ENDPOINT | No | Opik OTLP endpoint for cloud-based observability. |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/comet-ml/comet-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server