发现优秀的 MCP 服务器

agent-sleep

Enables AI agents to persist and recall episodic memories across sessions, consolidating experiences into reusable rules and lessons to reduce repeated mistakes and improve task performance.

mcp-arcgis-lorain

Enables searching and querying Lorain County, Ohio open geospatial datasets including parcels, addresses, zoning, and public works via ArcGIS Feature Services.

mitos

Enables AI agents to record and retrieve architectural decision records, check precedent before making decisions, and avoid repeating past mistakes or contradicting settled choices.

Porkbun MCP Server

Exposes the Porkbun v3 API as MCP tools for AI agents to manage domains, DNS, SSL, URL forwarding, and account settings.

datalox-gated-runtime

This MCP server provides a stateful, resettable, verifiable API runtime that gates every tool call, enabling agents to run long workflows against provider-shaped environments without live provider write access. It records decisions, side effects, and outcome evidence for replayable, verifiable benchmark runs.

mcp-json-reader

MCP server for reading, querying, and filtering local JSON files with extended JSONPath syntax, supporting sorting, aggregations, and complex conditions.

KappaML MCP Server

Exposes the KappaML API as tools for AI assistants, enabling user management, model operations, predictions, learning, forecasting, metrics, and checkpoint management.

Archive Search

Enables semantic search across conversation archives via MCP, allowing AI clients to retrieve relevant past conversations using vector embeddings and text fallback.

Cowboy MCP

Open-source WordPress plugin that turns any site into a Streamable HTTP MCP server. Manage posts, WooCommerce, and more from Claude Code, Codex, or Cursor — no Node.js

Apifox Filter MCP Server

Precisely filter and fetch API documentation from Apifox or any OpenAPI URL, reducing context bloat by fetching only needed endpoints.

twitter-mcp

Enables AI assistants to interact with Twitter/X using session cookies. Supports posting, searching, managing tweets, viewing trends, and user profiles.

DataHub MCP Server

Enables AI agents to search, explore data lineage, understand business context, and generate SQL queries across an organization's data ecosystem.

Research Assistant

Enables searching arXiv papers, extracting paper information, listing paper topics, and generating structured research prompts through MCP tools, resources, and prompts.

SearchAPI MCP Server

Model Context Protocol server that enables AI assistants like Claude to access searchapi.io API for searching Google Maps, flights, hotels, and other web information.

Weather Forecast MCP Server

Provides real-time weather and forecast tools backed by Open-Meteo API, enabling natural-language weather queries and smart predictions like umbrella recommendations through Databricks Agent Bricks.

OpenLandMap MCP Server

Provides access to the OpenLandMap STAC catalog, offering over 100 global environmental datasets including soil, climate, and vegetation data. It enables AI agents to discover, search, and retrieve Cloud-Optimized GeoTIFFs for global geospatial analysis.

knowledge-base-mcp

A lightweight personal knowledge base MCP server that lets clients store, search, organize, and summarize research notes from a local JSON file.

File System Utility MCP Server

Enables interaction with the local file system and retrieval of system information. Provides tools for listing directories, reading files, getting current time, and basic greeting functionality.

Interactive Voice MCP Server

Enables voice-based interactions with Claude by converting text to speech using Kokoro TTS and transcribing user responses using NVIDIA NeMo ASR, creating interactive voice dialogues.

galaxy-maps-mcp

Enables validation, saving, publishing, and inspection of Galaxy Maps courses from local JSON files via Firebase integration.

VidMCP

MCP server for video editing with text-prompt subject segmentation and compositing effects behind subjects. Enables agent-driven video creation and education animations.

agent-inbox-mcp

MCP server that lets AI agents manage an Agent Inbox queue via natural language. It supports listing pending items, adding new URLs with notes, and marking items as reviewed or deleted.

codecrafting-cloudflare-mcp

Enables read-only access to Cloudflare analytics for the codecrafting.fr zone, providing traffic, threats, and path attack data via local MCP tools for Claude Code.

Media Generator MCP

Enables image and video generation from text, image editing, and text-to-video workflows using AI models via OpenRouter and fal.ai.

WindTools MCP Server

Okay, I understand. You want me to translate the following English text into Chinese: "Your own codebase tools like code semantic search" Here are a few possible translations, depending on the nuance you want to convey: **Option 1 (Most literal and general):** * **你自己的代码库工具，例如代码语义搜索 (Nǐ zìjǐ de dàimǎ kù gōngjù, lìrú dàimǎ yǔyì sōusuǒ)** * This is a direct translation. "你自己的代码库" means "your own codebase," "工具" means "tools," "例如" means "for example," and "代码语义搜索" means "code semantic search." **Option 2 (Slightly more natural flow):** * **像代码语义搜索这样的，你自己的代码库工具 (Xiàng dàimǎ yǔyì sōusuǒ zhèyàng de, nǐ zìjǐ de dàimǎ kù gōngjù)** * This emphasizes the "like" part a bit more. "像...这样的" means "like... such as." **Option 3 (Focus on the benefit/purpose):** * **用于你自己的代码库的工具，比如代码语义搜索 (Yòng yú nǐ zìjǐ de dàimǎ kù de gōngjù, bǐrú dàimǎ yǔyì sōusuǒ)** * This emphasizes that these tools are *for* your codebase. "用于...的" means "used for..." and "比如" means "for example." **Which option is best depends on the context.** If you're simply listing examples, Option 1 or 2 is fine. If you're emphasizing the purpose of the tools, Option 3 might be better. Therefore, I recommend **Option 1 (你自己的代码库工具，例如代码语义搜索)** as a good general translation.

blob-storage

A lightweight MCP data broker that stores large binary payloads under a UUID, enabling MCP clients and agents to exchange massive results without flooding the LLM context window.

spring-ai-mcp-client

使用 Spring AI 和 Anthropic Claude 模型的 MCP 客户端应用程序。它与支持 MCP 协议的服务器集成，以实现 AI 驱动的聊天互动。

multi-model-mcp

An MCP server that exposes tools for sub-agent style reasoning across multiple LLM providers, enabling delegation of prompts to various models and running critique loops, debates, red-teaming, and answer ranking.