"scikit-learn" matching MCP servers:

Enables classifying electricity meter days as active, standby, off, or unsure from 96 fifteen-minute kWh readings plus a meter reference, with batch support for up to 31 days and model metadata. Runs fully offline as a frozen scikit-learn classifier, exposing single-day and batch classification plus model-info tools over STDIO or HTTP.

A monorepo for learning the Model Context Protocol with TypeScript, featuring example MCP servers for weather data and tax calculation.

Enables AI clients to search a personal corpus, read relevant source passages, and answer questions with traceable evidence from imported sessions, notes, and articles.

Enables AI assistants to locally process images with tools for cropping, zooming, enhancement, edge detection, segmentation, and text region extraction, all without external API keys. It uses PIL, OpenCV, and scikit-image for robust image analysis.

Provides tools for training, managing, and making predictions with scikit-learn's HistGradientBoostingClassifier models. It allows users to handle model lifecycles, including creation, evaluation, and serialization, via the Model Context Protocol.

An MCP server that provides AI trading agents with persistent, outcome-weighted memory to learn from historical performance and detect behavioral biases. It enables agents to automatically adjust strategies and optimize position sizing based on context-aware recall of past trade outcomes.

Enables AI coding agents to learn, from locally read lockfiles, what changes between the dependency version installed and a target version, which of the user's files that upgrade touches, and which vulnerabilities it resolves. It also performs OSV-matched vulnerability scans, ranks upgrade plans, and stores decision memory, running entirely on the user's machine with no account or API keys.

Shared memory layer for AI coding agents to store and recall learned information across sessions and tools.

Enables LLM agents to interact with the Lean theorem prover through the Language Server Protocol, providing tools for analyzing Lean projects, accessing diagnostics, goal states, documentation, and searching for theorems using both local and external search services.

An agent-native teaching OS that gives AI assistants a persistent classroom with courses, lessons, flashcards, and graded exercises via MCP tools.

Extracts and stores documentation content from Microsoft Learn and GitHub URLs into PocketBase with full-text search, metadata preservation, and automatic collection management for easy retrieval and organization.

Provides access to a community knowledge base of 16k+ debugging solutions and 223+ reusable skills, plus auto-scanned project-specific knowledge bases that learn and store solutions as you work.

Create videos from scripts and storyboards, manage projects, and export completed videos through the VideoGen API. Runs locally with npx and authenticates with your VideoGen API key. Learn more: https://videogen.io/videogen-mcp

An MCP server implementation that helps Claude remember and learn from programming errors by storing, retrieving, and finding similar errors with full context.

MCP server for agentic interaction with the Lean theorem prover via LSP, providing tools for understanding, analyzing, and interacting with Lean projects.

A TypeScript-based MCP server that enables LLM agents to interact with Gel databases through natural language, providing tools to learn database schemas, validate and execute EdgeQL queries.

A custom MCP protocol service that enhances AI models by providing multilingual translation capabilities and resource management, allowing for automatic text extraction and translation through external APIs.

An MCP server for ingesting Lean Six Sigma PDFs into a searchable multimodal knowledge base.

mozg turns documentation into knowledge brains your agent queries over MCP instead of loading whole files into context. What makes it different: every brain sits an exam. Its goal becomes ~30 control questions, re-sat after every ingest — so 'trained 92%' is measured, not claimed, and the failing questions are listed publicly. Brains learn from use: searches that return nothing become exam questio

Implements Agentic Context Engineering to create self-improving AI coding assistants that learn from execution feedback and build persistent knowledge playbooks. Reduces token usage by 86.9% while improving code accuracy by 10.6% through incremental context updates.