发现优秀的 MCP 服务器

playwright-mcp

Provides browser automation capabilities for AI assistants, enabling web navigation, form filling, and data extraction through Playwright.

freshrss-mcp

An MCP server for reading and managing RSS feeds from a self-hosted FreshRSS instance, enabling listing feeds, fetching articles, and subscribing/unsubscribing through the FreshRSS API.

MCP Novel Game Server

A novel game server supporting multi-branch visual novel scenarios in English and Japanese, designed to help understand MCP Resources.

Playwright MCP

Enables browser automation and web scraping by exposing Playwright tools through an HTTP-based MCP server. Users can navigate pages, interact with web elements, capture screenshots, and extract structured content using a persistent Chromium instance.

solograph

Code intelligence MCP server for Claude Code providing multi-project code graph, semantic search, session history, knowledge base, and web search.

copilot-usage-mcp

Exposes GitHub Copilot premium request usage as an MCP tool, providing a breakdown by model and cost.

Port MCP Server

An MCP server that enables Claude to interact with Port.io's AI agent, allowing users to trigger the agent with prompts and receive structured responses including status, output, and action items.

Maya MCP

Maya MCP

test-server MCP server

镜子 (jìng zi)

Package Intel MCP Server

A Model Context Protocol server for querying package registries (npm, PyPI, crates.io) to retrieve metadata, release timelines, and maintenance signals.

visa-requirements

Enables querying passport visa rules for any nationality to destination pair.

mind-mem

Drop-in memory layer for AI coding agents, upgrading them from chat history to a governed Memory OS with hybrid search, contradiction detection, and safe governance.

superagentic

An MCP server that lets agents claim, work on, and finish units of work in a coordinated fleet, with lease and heartbeat protection, plus tools for orchestrators to define work and collect results.

SemaphoreUI MCP Server

Enables AI assistants to interact with SemaphoreUI for managing and running Ansible automation tasks through natural language commands.

sapphire-user-mcp

Exposes user profile data from the Sapphire Wellness App to AI assistants via MCP, providing tools for fetching health alerts, personalized recommendations, and partner service subscriptions.

promptpilot-mcp-server

Generate images, video, and audio directly in Claude Code, Cursor, Windsurf, or any MCP-compatible AI agent. 20+ models — Flux, GPT-Image-1, Imagen 4, Grok Imagine, Seedance, ElevenLabs TTS, and more. Free models work without an API key. Paid models require a Pollinations key.

Lambda Capture MCP Server

MCP server that enables semantic search over macroeconomic data using the Lambda Capture API.

mcp-x-intelligence

Read-only X/Twitter research MCP server allowing AI assistants to search viral content, analyze accounts, track trends, and discover niche leaders without requiring the official X API.

evalmine

Enables agents to run evals mid-task, providing tools to validate suites, execute model comparisons, and inspect calibration and win-rate reports.

cc-plugin-mcp

MCP server for accessing Claude Code plugins. Enables retrieving plugin lists and detailed information via MCP clients like Claude Desktop, Cursor.

blockworld

Enables AI agents to build voxel structures in a 3D world using primitive shape tools like boxes, cylinders, cones, spheres, and tubes.

@theyahia/travelpayouts-mcp

MCP server for the Travelpayouts (Aviasales) API. It provides 13 tools for flight search, price calendars, hotel search, and airport/airline/city lookup.

personal-health-mcp

Fetches body composition data (weight, body fat percentage) from the Tanita Health Planet API and exposes it as MCP tools for AI agents like Claude Desktop.

code-bridge

An MCP server that bridges Claude Desktop with Claude Code, allowing users to delegate tasks to Claude Code directly from Claude Desktop conversations, supporting both synchronous and background execution with session reuse.

Rust Docs MCP Server

镜子 (jìng zi)

Spanish Public Data MCP

MCP server for querying Spanish government open data APIs including grants, legislation, company registry, statistics, and open data catalog. Enables LLMs to access Spanish public information on-the-fly.

Giphy MCP Server

An auto-generated Multi-Agent Conversation Protocol Server that enables interaction with the Giphy API, supporting various transport modes and configurable through environment variables.

manim-mcp-server

This is a complex request! Generating animations like 3Blue1Brown with a single prompt is currently impossible with existing AI tools. 3Blue1Brown animations are meticulously crafted using a combination of programming (primarily Python with libraries like Manim), mathematical understanding, and artistic design. A single prompt simply cannot encapsulate the necessary detail and control. However, I can give you a *starting point* prompt that might generate *something* vaguely reminiscent, and then explain why it's unlikely to be successful and what you'd need to do to get closer to the desired result. **Prompt (for an image generation AI like DALL-E 3, Midjourney, or Stable Diffusion):** `"A dynamic, colorful animation frame showing a vector transforming a grid, inspired by 3Blue1Brown's style. Use a vibrant color palette, clean lines, and a focus on mathematical visualization. Include subtle motion blur to suggest movement. Emphasis on clarity and understanding."` **Why this will likely fall short:** * **Lack of Mathematical Understanding:** Image generation AIs don't "understand" the underlying mathematics. They can mimic visual styles, but they won't accurately represent mathematical concepts like linear transformations, eigenvalues, or calculus. The grid might be distorted, but not in a mathematically meaningful way. * **No True Animation:** This prompt will only generate a single image, not an animation. Creating an animation requires generating a sequence of images with controlled changes over time. * **Inability to Control Precision:** 3Blue1Brown animations are precise. Every line, every movement, is carefully calculated. Image generation AIs are inherently stochastic (random) and lack this level of control. * **No Narrative or Explanation:** 3Blue1Brown videos are more than just visuals; they tell a story and explain complex concepts. A single image can't convey that. * **Style Mimicry Only:** The AI will try to mimic the visual style (color palette, clean lines), but it won't understand the *purpose* of that style, which is to enhance understanding. **What you *would* need to do to get closer to a 3Blue1Brown-style animation:** 1. **Learn Manim (or a similar animation library):** This is the most important step. Manim is specifically designed for creating mathematical animations. It allows you to define objects, transformations, and animations with precise mathematical control. 2. **Break Down the Animation into Steps:** Plan the animation carefully. What concepts are you trying to illustrate? What sequence of transformations will best convey those concepts? 3. **Write Code:** Use Manim to write code that creates each frame of the animation. This will involve defining mathematical objects (vectors, matrices, graphs), specifying transformations (rotations, scaling, shearing), and controlling the timing and easing of the animations. 4. **Render the Animation:** Manim will render the code into a sequence of images, which you can then combine into a video. 5. **Add Narration and Music:** Finally, add narration and music to explain the concepts and enhance the viewing experience. **In summary:** While AI image generation can create visually appealing images inspired by 3Blue1Brown, it cannot replicate the mathematical accuracy, precision, and explanatory power of a true 3Blue1Brown animation. You'll need to learn programming and mathematical animation techniques to achieve that level of quality. **Translation of the prompt to Chinese:** `"生成一个动态的、色彩鲜艳的动画帧，展示一个向量变换一个网格，灵感来自 3Blue1Brown 的风格。 使用充满活力的调色板、干净的线条，并专注于数学可视化。 包括微妙的运动模糊来暗示运动。 强调清晰度和理解力。"` (Pinyin: `"Shēngchéng yīgè dòngtài de, sècǎi xiānyàn de dònghuà zhēn, zhǎnshì yīgè xiàngliàng biànhuàn yīgè wǎnggé, línggǎn láizì 3Blue1Brown de fēnggé. Shǐyòng chōngmǎn huólì de tiáosèbǎn, gānjìng de xiàntiáo, bìng zhuānzhù yú shùxué kěshìhuà. Bāokuò wēimiào de yùndòng móhú lái ànshì yùndòng. Qiángdiào qīngxīdù hé lǐjiě lì."`)