发现优秀的 MCP 服务器

README Insight MCP

Provides tools to summarize README files from local paths or public Git repositories into structured JSON summaries. It enables users to quickly extract key facts and project overviews from documentation through automated tool calls.

mcp-wait

Provides a wait tool for AI agents to pause execution until a time duration elapses or a process terminates, useful for polling and waiting for builds/deployments.

proxmox-mcp

A Python MCP server for Proxmox VE that lets AI agents read cluster status, power guests on/off, and provision new VMs/containers through natural language, while preventing any destructive actions.

chuk-mcp-vfs

Provides virtual filesystem workspaces with full file operations (read, write, ls, tree, mkdir, rm, mv, cp, cd, pwd, find, grep) and checkpoint management. Supports multiple storage providers (memory, filesystem, sqlite, s3) with session, user, and shared scopes.

bawbel-mcp

Bawbel MCP Server lets any agent scan MCP servers and skill files for security vulnerabilities mid-conversation. Seven tools covering server-card scanning, conformance scoring, rug pull detection, and AVE threat intelligence queries. Powered by the AVE standard with OWASP MCP Top 10 mapping on every finding. Free, Apache 2.0, no API key required.

OpenSCAD MCP Server

An intelligent assistant for 3D modeling with OpenSCAD and 3D printing workflow, including a Gradio app to test different LLMs.

altium-mcp

Use Claude to control or ask questions about your Altium project.

einvoice-mcp

MCP server for German e-invoice compliance (XRechnung 3.0 & ZUGFeRD 2.x) enabling AI agents to validate, generate, parse, and check compliance of electronic invoices per EN 16931.

mc-mcp-server

Enables AI-driven interactions with Minecraft through a WebSocket-based server and MCP protocol, allowing external MCP clients and in-game chat to trigger AI tools.

lineworks-mcp

MCP server for LINE WORKS that enables accessing user profiles, calendars, tasks, groups, and notes via OAuth 2.0.

Frontier Intelligence

A personal monitoring and trend synthesis system that collects signals from multiple sources, processes them through LangChain/GigaChat, stores them in vector and knowledge graphs, and delivers insights via MCP to Codex/Claude projects with workspace isolation.

postgres-aiops

Governed PostgreSQL DBA operations — slow-query, bloat, and blocking-lock RCA, index management, vacuum/analyze, and replication lag, with unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

limelink-mcp-server

MCP server for LimeLink dynamic link management, enabling creation, lookup, and management of dynamic links with documentation resources and prompt templates.

aparser-mcp

Enables AI agents to drive parsing tasks via A-Parser, including running SERP queries, queueing bulk jobs, polling, and fetching results.

who_reps-mcp

Given a U.S. street address, returns the people who represent it (U.S. Senators, House member, Governor, and state legislators) using free public data, with no API keys required for federal officials.

Elasticsearch MCP Server

MCP server that provides tools and resources to interact with Elasticsearch clusters, including listing indices, searching, and retrieving mappings.

FAL Reve MCP Server

Enables high-quality text-to-image generation and image editing using FAL AI's Reve model. Supports batch processing, multiple aspect ratios and formats, with automatic local image downloads and both real-time and async processing modes.

sombra-mcp

A stdio-to-HTTP bridge for connecting to Sombra's remote MCP server, enabling AI agents to save, search, and organize web content.

recipe-tools

Enables extraction of recipes from PDFs or JPG files and conversion into structured HTML, with interactive region selection and OCR via a web GUI.

MCP Magic UI

一个模型上下文协议（Model Context Protocol，MCP）服务器，提供对 Magic UI 组件的访问，允许 AI 助手和其他 MCP 客户端发现和使用来自 Magic UI 设计系统的 UI 组件。

blender-mcp-enhanced

Connects Blender to Claude AI through the Model Context Protocol for AI-assisted 3D modeling, procedural geometry creation, and persistent multi-turn workflows with shared context and advanced tool chaining.

GitHub DeepWiki MCP Server

This MCP server provides detailed GitHub repository information by integrating with mcp.deepwiki.com and GitHub API to fetch repository wiki content, README files, and enable intelligent question-answering about repositories.

vid-agent-mcp

Enables Claude to transcribe Bilibili videos, search by intent, and analyze local video files, returning structured summaries with key points and verdicts.

mcp-server-google-cloud-logging

好的，以下是一些关于如何使用 gcloud 从 Logging 获取日志的说明： **基本命令：** 最基本的命令是 `gcloud logging read`。 它会从 Logging 中读取日志条目并将其打印到您的终端。 ```bash gcloud logging read ``` 这会显示最近的日志条目。 **常用选项：** * **`--limit`**: 限制返回的日志条目数量。 例如，只显示最近的 10 个条目： ```bash gcloud logging read --limit 10 ``` * **`--format`**: 控制输出格式。 常用的格式包括 `text` (默认), `json`, 和 `yaml`。 `json` 格式对于进一步处理日志数据非常有用。 ```bash gcloud logging read --limit 10 --format json ``` * **`--freshness`**: 指定日志条目的时间范围。 例如，只显示过去 5 分钟的日志： ```bash gcloud logging read --freshness 5m ``` 可以使用 `s` (秒), `m` (分钟), `h` (小时), `d` (天) 作为单位。 * **`--project`**: 指定要查询的 Google Cloud 项目。 如果未指定，则使用当前活跃的项目。 ```bash gcloud logging read --project your-project-id ``` * **`--order`**: 指定日志条目的排序方式。 可以是 `asc` (升序，最早的日志在前) 或 `desc` (降序，最新的日志在前，默认值)。 ```bash gcloud logging read --order asc ``` **使用过滤器：** `gcloud logging read` 最强大的功能是使用过滤器来精确地选择您需要的日志条目。 过滤器使用 Logging 查询语言。 * **基本过滤：** * 按日志名称过滤： ```bash gcloud logging read "logName:projects/your-project-id/logs/your-log-name" ``` 将 `your-project-id` 替换为您的项目 ID，将 `your-log-name` 替换为日志的名称 (例如，`stdout`, `stderr`, 或自定义日志名称)。 * 按严重程度过滤： ```bash gcloud logging read "severity>=ERROR" ``` 这将显示所有严重程度为 `ERROR` 或更高的日志条目 (例如，`ERROR`, `CRITICAL`, `ALERT`, `EMERGENCY`)。 * 按文本内容过滤： ```bash gcloud logging read "textPayload:\"error message\"" ``` 这将显示所有包含 "error message" 的日志条目。 注意需要使用双引号转义。 * **更复杂的过滤：** * 组合多个条件： ```bash gcloud logging read "logName:projects/your-project-id/logs/your-log-name AND severity>=WARNING" ``` * 过滤特定资源： ```bash gcloud logging read "resource.type=gce_instance AND resource.labels.instance_id=your-instance-id" ``` 将 `your-instance-id` 替换为您的 GCE 实例 ID。 * 过滤 JSON 有效负载中的字段： ```bash gcloud logging read "jsonPayload.status = \"error\"" ``` 假设您的日志条目有一个 JSON 有效负载，其中包含一个名为 `status` 的字段。 **示例：** 1. 获取过去 1 小时内来自特定日志的错误日志，并以 JSON 格式输出： ```bash gcloud logging read --freshness 1h --format json "logName:projects/your-project-id/logs/your-log-name AND severity>=ERROR" ``` 2. 获取特定 GCE 实例的日志，并将其保存到文件中： ```bash gcloud logging read "resource.type=gce_instance AND resource.labels.instance_id=your-instance-id" > instance_logs.txt ``` **重要提示：** * **权限：** 确保您拥有访问 Logging 数据的适当权限。 您可能需要 `roles/logging.viewer` 或更高级别的角色。 * **查询语言：** 熟悉 Logging 查询语言对于编写有效的过滤器至关重要。 请参阅 Google Cloud 文档以获取完整的语法和功能：[https://cloud.google.com/logging/docs/view/advanced-queries](https://cloud.google.com/logging/docs/view/advanced-queries) * **性能：** 复杂的过滤器可能会影响查询性能。 尽量保持过滤器简洁高效。 希望这些信息对您有所帮助！ 如果您有任何其他问题，请随时提出。

Stability AI MCP Server

镜子 (jìng zi)

Ronin Defense MCP

Detects and sanitizes hidden-payload attacks in MCP communications to protect LLMs in agentic IDEs from malicious prompt injection and adversarial content delivery.

condensation-mcp

Enables users to assess condensation and mold risk for building surfaces using physics-based calculations (dew point, surface temperature, critical thresholds), with support for real-time weather data and prescription generation.

mcp-alphafold

Provides programmatic access to AlphaFold protein structure predictions and UniProt data, enabling users to retrieve protein structures, summaries, and annotations through natural language.

UniAuto MCP Server

具有自修复功能的通用测试自动化 MCP 服务器，并集成了 Smithery.ai。