A
licenseA
qualityB
maintenanceA scientific experiment log MCP server for AI agents that stores predictions, causal claims, and verdicts, enabling queryable causal maps and calibration of intuition over diagnostics.
17
MIT
Best MLflow MCP Servers
MLflow is an open-source platform for managing the end-to-end machine learning lifecycle, including experiment tracking, reproducible runs, and model deployment.
Why this server?
Allows referencing MLflow runs as external run stores for experiments.
Why this server?
Provides tools for interacting with MLflow, enabling AI agents to retrieve deployment history, diff deployments, and execute rollbacks on the MLflow model registry.
AlicenseAqualityBmaintenanceMCP server for autonomous MLOps incident response, enabling drift detection, deployment history analysis, and human-approved rollback execution via gated tools.7MITWhy this server?
Provides a read-only adapter for MLflow, enabling agents to reference MLflow runs as evidence in research records.
AlicenseBqualityBmaintenanceAgentRoots is an MCP server for agent continuity that preserves goals, findings, and evidence across sessions. It enables agents to propose, review, and reuse compact, evidence-backed state instead of replaying transcripts.9Apache 2.0Why this server?
Provides tools for querying, debugging, and evaluating MLflow traces generated during research and analysis workflows.
AlicenseAqualityDmaintenance45-tool MCP server for video analysis, deep research, content extraction, web search, and Weaviate knowledge storage. Powered by Gemini 3.1 Pro.345322MITWhy this server?
Discovers and scans MLflow platforms to identify security risks and verify the provenance of AI models.
Why this server?
Provides comprehensive tools for managing MLflow experiments, runs, registered models, model versions, logged models (MLflow 3), traces, assessments, webhooks, and prompt-optimization jobs. Includes aggregation tools and MCP resources for efficient AI-driven workflows.
AlicenseBqualityAmaintenanceMLflow MCP — 82 tools for experiments, runs, registered models, traces, assessments. MLflow 3 GenAI traces support with analyze-failed-traces workflow Prompt.82851MITWhy this server?
Provides tools for managing MLflow experiments, runs, metrics, parameters, artifacts, logged models, and the model registry, enabling LLMs to interact with MLflow tracking servers.
AlicenseAqualityBmaintenanceA Model Context Protocol server that enables LLMs to interact with MLflow tracking servers, allowing users to query experiments, analyze runs, compare metrics, manage the model registry, and promote models through natural language.4014MITWhy this server?
Provides tools for managing MLflow experiments, runs, models, registered models, model versions, and webhooks.
AlicenseBqualityCmaintenanceExposes Databricks REST APIs as MCP tools for managing and querying a Databricks workspace, including clusters, jobs, SQL, Unity Catalog, and more.100MITWhy this server?
Provides tools for retrieving training run metrics from MLflow experiments (planned integration).
FlicenseAqualityBmaintenanceEnables semantic search across personal PDF paper collections with page-level citations, allowing users to query their library from any MCP-capable client.9