MLflow MCP Server
by kkruglik
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MLFLOW_TRACKING_URI | Yes | MLflow tracking server URL, e.g. http://127.0.0.1:5000 | |
| MLFLOW_TRACKING_TOKEN | No | Bearer token (Databricks or token-based setups) | |
| MLFLOW_TRACKING_PASSWORD | No | HTTP Basic Auth password (MLflow built-in auth) | |
| MLFLOW_TRACKING_USERNAME | No | HTTP Basic Auth username (MLflow built-in auth) |
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/kkruglik/mlflow-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server