"UML" matching MCP servers:

Enables AI agents to check URL safety before fetching content, using Google Web Risk, URLhaus, PhishTank, and AI analysis to return SAFE/SUSPICIOUS/DANGEROUS verdicts.

Exposes a time series forecasting model as an MCP tool with built-in audit logging for every call, enabling trustworthy autonomous forecasting.

A local RAG context optimizer MCP server that filters retrieved context to the minimum an LLM needs to answer correctly, using a cross-encoder and optional calibration.

Exposes local Umi-OCR v2 capabilities to AI agents via MCP, enabling image text extraction, batch OCR, PDF OCR, and status checks without manually starting the service.

Enables security teams to run controlled adversarial penetration tests against authorized ML/LLM API endpoints, scoring responses and generating evidence for compliance frameworks such as SOC 2, ISO 27001, and GDPR.

Analyze YouTube, TikTok, and Instagram videos from URL. Extracts transcripts, generates AI insights, and pulls tutorial steps from any video link.

Enables interaction with Comet ML's experiment tracking platform through the Model Context Protocol, providing tools for experiment management, project organization, and advanced search.

Enables agents to track ML experiments with a reproducible write contract, internal git snapshots, and a queryable knowledge graph, plus a live web UI for humans.

基于FastMCP和scikit-learn构建的机器学习MCP服务器，提供30个工具覆盖分类、回归、聚类、降维、模型评估和数据预处理。

Generates technical documentation and diagrams (C4, UML, flowcharts, Gantt, etc.) using MCP protocol, with Docker-based tooling and optional AI image generation via DALL-E 3.

Enables natural-language evaluation, explanation, and reporting of any trained ML model, including performance metrics, prediction insights, drift detection, and PDF report generation.

Query your MLflow experiments in plain English using Claude Desktop. No dashboards, no SQL — just ask.

MCP server that diagnoses ML model regressions by correlating drift reports, eval runs, and deploy logs, providing evidence-cited incident reports through a set of investigation tools.

An MCP server that gives AI agents the ability to profile a CSV, define an ML task, tune XGBoost and LightGBM with Optuna, and produce a markdown report with feature importance, all from natural language.

Deploys an MCP server on Azure Container Apps that exposes Azure ML managed online endpoints as tools, enabling AI agents like Azure AI Foundry to invoke machine learning models via natural language.

Self-hosted ML inference MCP server providing embeddings and summarization tools using sentence-transformers and Ollama, with low-latency preloaded models and API-key authentication.

Enables LLMs to manage and run machine learning training jobs on a remote server, including syncing code, submitting experiments, monitoring progress, reading TensorBoard metrics, and receiving completion notifications.

Monitors ML models in production for data drift and performance degradation, providing automated alerts and retraining recommendations.

Enables graph-based fraud propagation scoring for clinical diagnostics, diffusing risk across entities with a deterministic fallback when the ML model is unavailable.

Enables running ML experiments from a local laptop by coordinating GitHub for code, Kaggle for data and GPU training, Weights & Biases for tracking runs, and Google Drive for small artifacts.