"osu!" matching MCP servers:

A zero-data MCP server for LLM fine-tuning, providing 64 tools across 10 dimensions to prepare, build, train, evaluate, secure, package, and deliver fine-tuned models without ever accessing client data.

ChemMCP is an easy-to-use and extensible chemistry toolkit for LLMs and AI assistants, enabling molecular analysis, property prediction, and reaction synthesis tasks without domain-specific training.

Enables Claude to learn a user's writing style from personal samples and retrieve style context, exemplars, and profiles for rewriting and code-comment guidance through MCP.

Measurement uncertainty MCP server for ISO/IEC 17025 and KOLAS-accredited laboratories. GUM/MCM/QMC engine + 9 calibration templates (TEM/SEM-EDS/AFM/OCD nano-metrology) + reverse_uncertainty (novel within prior-art search) + Ed25519 audit signatures + W3C PROV-O provenance. v0.6.0, 36 passing tests on Python 3.10–3.12.

MCP server providing persistent memory, semantic search, versioned storage, webhook fanout, and unified LLM routing for AI agents via FastAPI runtime with multiple backend options.

MCP-native evolution control plane that discovers, tests, governs, versions, and promotes improved AI agents. Integrates with LocalLLM-MCP for real or simulated model evaluation.

An AI-driven platform for analyzing Polymarket prediction markets using on-chain data, offering smart money tracking, sentiment analysis, and arbitrage detection via natural language queries.

Wine pairing intelligence for AI assistants. 7 MCP tools for sommelier-grade wine recommendations: pair wines with meals, ingredients, or recipe URLs, reverse pairing, group dinner planning, and search. Powered by a proprietary Wine DNA algorithm with 600+ wine archetypes. Supports API key and x402 (USDC on Base) autonomous agent payments.

Read-only relational-readiness preflight for AI agents evaluating market trust, permission, evidence gaps, pilot readiness, and scale readiness in African and other high-context markets.

MCP server for SeeAny Sun enabling product image generation, smart creation, task polling, and download via natural language, with demo mode for offline simulation.

Enables Claude Code, Cursor, Codex and other MCP clients to generate and edit images and videos directly in a project using AI subscriptions the user already pays for, without API keys or extra billing. Also provides local media tools such as background removal, video editing for social formats, and automatic resizing and optimization of results.

A Model Context Protocol (MCP) gateway for running Claude Code, Codex, Gemini, Grok, and Mistral (Vibe) CLIs from one MCP endpoint, with durable async jobs, session continuity, cache-aware prompting, observability, and personal-appliance setup tooling. Why developers try it: one local MCP endpoint for cross-LLM validation, multi-agent coding workflows.

법마디(Lawmadi) OS — Korean Legal AI with 60 specialized agents and real-time statute verification via law.go.kr. Free: 2 queries/day. Korean & English.

Integrates Base44 data management, Theta GPU compute and blockchain, and Wave OS intelligence into a single MCP server, enabling AI assistants to perform CRUD, AI inference, smart contract operations, and agent orchestration.

Enables AI coding agents to maintain structured, persistent memory as a typed-edge knowledge graph over contexts, decisions, and tasks, with deterministic auto-threading, trust signals, and replayable story recall. It also exposes a token-lean MCP gateway for on-demand tool discovery, helping agents preserve causal project context across sessions.

Lets AI agents generate images and videos through a self-hosted studio connected to the user's own fal.ai, Kie.ai or Higgsfield API keys, with tools for exploring models, submitting image and video jobs, waiting on results and importing media from URLs. Runs over HTTP with bearer-token authentication, so agents such as Claude Code, Codex, Cursor or Claude Desktop can create and retrieve media while provider keys stay encrypted server-side.

Enables Claude and other MCP clients to manage Pankow organizations, projects, test cases, and CI/runs, configure AI targets, and run LLM evaluations directly from an agent.

Enables agents to complete supported search, extraction, summarization, translation, and classification tasks by choosing an eligible provider, tool, or MCP route, executing it, applying bounded fallback when appropriate, and recording the outcome.

Enables MCP clients to discover and invoke domain-specialized tools for humanitarian emergency response, public health, research synthesis, grant proposals, human rights monitoring, maternal health, and SOP synthesis. It supports JSON-RPC 2.0 over Streamable HTTP for structured, privacy-conscious field outputs and voice-friendly summaries.

Provides persistent memory for Claude Code, automatically extracting and surfacing relevant context from past sessions to avoid re-explaining issues and decisions.

A collection of miscellaneous tools for Claude, Cursor, and MCP-compatible clients. Includes OCR (Optical Character Recognition) capabilities leveraging the Google Gemini API.

Enables evaluating AI applications, inspecting reliability evidence, and gating releases from development and CI workflows.

An MCP server that provides authorization middleware for AI agents using private data, enabling consent management on Aleo and local private inference with persistent policy storage.