MLflow MCP Server
Related Servers
Alternatives to MLflow MCP Server
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceA natural language interface for MLflow that allows users to query and manage their machine learning experiments and models using plain English through the Model Context Protocol.11-
- FlicenseNot gradedqualityFmaintenanceA Model Context Protocol server that enables LLMs to interact with Databricks workspaces through natural language, allowing SQL query execution and job management operations.50-
- FlicenseAqualityDmaintenanceA Model Context Protocol server that lets LLM clients answer business questions in natural language over a Databricks dataset without writing SQL by hand.1-
- AlicenseAqualityBmaintenanceA unified Model Context Protocol server for data engineering and analytics that lets LLM clients query, profile, transform, and visualize data using DuckDB and PySpark, while keeping raw data out of the model's context through read-only, bounded, and audited operations.81MIT

MCP TapData Serverofficial
FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables Large Language Models to access and interact with database connections, including viewing schemas and performing CRUD operations on connected databases.-- AlicenseBqualityFmaintenanceA Model Context Protocol server that enables AI assistants to query Prometheus metrics, discover available data, and analyze system performance through natural language interactions.555 npmMIT
TDQS
Scored across 40 tools
Each tool targets a distinct MLflow resource or action, such as experiments, runs, models, artifacts, or tags. Despite a large number of tools, their descriptions clearly differentiate them (e.g., get_run vs get_runs vs query_runs). There is minimal overlap in functionality.
Tool names follow a consistent verb_noun pattern (e.g., get_experiment, set_model_alias, delete_run). Exceptions like 'health' are single-purpose and follow the pattern. Overall naming is predictable and clear.
40 tools is above the typical well-scoped range (3-15), but the domain (MLflow) has many entities and operations, making a larger surface reasonable. However, some tools could be merged or omitted to reduce cognitive load.
The tool surface covers CRUD for experiments, runs, model registry, tags, and artifacts, plus search and comparisons. Minor gaps exist, such as no direct create_run or update_experiment, but these are managed elsewhere in MLflow.