"Fing" matching MCP servers:

Enables AI agents to turn song requests into ready-to-send audio files by searching and downloading tracks, trimming clips, separating vocals, applying RVC voice conversion, and mixing the result with accompaniment. Supports original-clip and full-cover modes with environment self-checks.

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.

Enables AI agents to discover and execute solar energy domain tools such as solar cell simulation, perovskite parameter/bandgap/aging prediction, RAG knowledge retrieval, and curve/table generation through MCP.

Gives Claude Code, Claude Desktop, Cursor and any other MCP client a local sound studio that turns plain-language requests into background music, instrument loops and sound effects, then re-styles, regenerates or extends them and exports seamless loops, fades and loudness-normalized WAV, OGG or FLAC files. Everything runs on Apple Silicon with no cloud service and no API key.

Enables transcribing public Douyin videos to text using a local AI model, providing read-only tools for transcription, search, and listing.

Enables agents to run bounded research experiments across configurable model providers and search modes, with cost estimation, budget gating, durable paginated results, idempotent runs, and cancellation. Exposes seven tools for discovering targets, estimating and starting runs, polling status, and retrieving citations, sources, and usage from stored evidence.

Enables querying Microsoft's Bing Copilot AI to retrieve structured answers, citations, and brand mention checks as JSON, designed for AEO/GEO monitoring.

Real-time financial narrative tracking for AI agents — clustering news into structured narratives, measuring sentiment momentum, and mapping portfolio risk across 109 US equities.

Enables an MCP-capable desktop client to inspect canvas state and action schemas, execute design edits and submissions, and read rewards from a deterministic design-canvas environment over stdio.

Lets any MCP-compatible agent use Google Colab or Jupyter runtimes as an execution backend, enabling code execution, notebook management, package installation, hardware introspection, training jobs, and file handling.

Enables agents and MCP clients to send local image files or image URLs with an optional question and receive text answers through an analyze_image tool. Runs against a local Ollama vision model by default and automatically falls back to Volcano Ark Doubao (or any OpenAI-compatible endpoint) when cloud credentials are configured.