发现优秀的 MCP 服务器

Langgraph-MCP Client for Postgresql Example

Okay, here's a translation of "LangGraph implementation interacting with a PostgreSQL MCP Server" into Chinese, along with some considerations for different nuances: **Option 1 (Most Direct and Common):** * **Simplified Chinese:** LangGraph 与 PostgreSQL MCP 服务器交互的实现 * **Traditional Chinese:** LangGraph 與 PostgreSQL MCP 伺服器互動的實作 * **Explanation:** * `LangGraph`: We keep the English name as it's a specific technology. It's common practice to keep technical terms in English, especially if a widely accepted Chinese translation doesn't exist. * `与...交互 (yǔ... jiāohù)`: "Interacting with..." This is a standard and clear way to express interaction. * `PostgreSQL MCP 服务器 (PostgreSQL MCP fúwùqì)`: "PostgreSQL MCP Server". Again, we keep the specific names in English. `服务器 (fúwùqì)` means "server". * `的实现 (de shíxiàn)`: "...'s implementation". This is the standard way to say "implementation of...". * `互動 (hùdòng)` is the traditional Chinese equivalent of `交互 (jiāohù)`. * `實作 (shízuò)` is the traditional Chinese equivalent of `实现 (shíxiàn)`. **Option 2 (More Descriptive, but potentially longer):** * **Simplified Chinese:** 使用 LangGraph 实现与 PostgreSQL MCP 服务器的数据交互 * **Traditional Chinese:** 使用 LangGraph 實現與 PostgreSQL MCP 伺服器的資料互動 * **Explanation:** * `使用...实现 (shǐyòng... shíxiàn)`: "Using... to implement..." * `数据交互 (shùjù jiāohù)`: "Data interaction". This emphasizes that the interaction involves data. * `資料互動 (zīliào hùdòng)` is the traditional Chinese equivalent of `数据交互 (shùjù jiāohù)`. **Option 3 (Focus on Integration):** * **Simplified Chinese:** LangGraph 与 PostgreSQL MCP 服务器的集成实现 * **Traditional Chinese:** LangGraph 與 PostgreSQL MCP 伺服器的整合實作 * **Explanation:** * `集成 (jíchéng)`: "Integration". This emphasizes the act of combining LangGraph and the PostgreSQL MCP server. * `整合 (zhěnghé)` is the traditional Chinese equivalent of `集成 (jíchéng)`. **Which option is best depends on the context:** * **Option 1** is the most straightforward and generally suitable. * **Option 2** is good if you want to explicitly mention data interaction. * **Option 3** is good if you want to emphasize the integration aspect. **Important Considerations:** * **Target Audience:** Who are you writing for? If it's a highly technical audience, keeping the English terms is fine. If it's a more general audience, you might consider providing brief explanations of LangGraph and MCP. * **Consistency:** If you're using this phrase in a larger document, be consistent with your terminology. * **MCP:** What does "MCP" stand for? If you know the full name, you could translate that part as well, but only if it's a well-known term in Chinese. Otherwise, keep it as "MCP". I recommend using **Option 1** unless you have a specific reason to choose one of the others. It's clear, concise, and uses standard terminology. Remember to choose the Simplified or Traditional Chinese version based on your target audience.

MonkeyPlanner

Local-first kanban and approval-gate issue tracker with a native MCP server (13 tools). Humans approve; agents claim, QA, and complete issues. Single Go binary + SQLite.

YRB-HES Evidence MCP

A read-only MCP server for evidence retrieval in Yellow River Basin human–earth systems reviews, exposing PostgreSQL-backed tools for searching and comparing evidence, entities, and spatiotemporal data while preserving source provenance.

mcp-gads

Enables querying and managing Google Ads campaigns, keywords, assets, and more via natural language, with support for multiple MCP clients.

Jokes MCP Server

Enables users to fetch various types of jokes including Chuck Norris and Dad jokes through an MCP server that integrates with Microsoft Copilot Studio and GitHub Copilot.

Scopus MCP Server

Provides access to the Elsevier Scopus API, enabling AI assistants to search for academic papers, retrieve detailed abstracts, and look up author profiles. It facilitates bibliometric research and scholarly data analysis through natural language commands.

Outscraper MCP Server

A Model Context Protocol server that provides access to Outscraper's data extraction services, implementing 8 tools for extracting data from Google services and domains including Maps, Reviews, Search, and contact information.

CO2 Sensor MCP Server

A Node.js application that provides a JSON-RPC interface to interact with CO2 sensor data, working in both simulation mode and with real Raspberry Pi Pico hardware connections.

AIE7-hw13-mcp

MCP server using Tavily API for web search, enabling web search queries via stdio transport.

trinity-local

Enables running AI councils across Claude, GPT, and Gemini, synthesizing answers based on your personal taste lens, all locally without an API key.

N-central MCP Server

Exposes N-able N-central REST API as MCP tools for managing devices, organizations, users, and more, with support for read-only, write, and full write modes.

Mega Agent MCP

A unified MCP server providing tools for web search, GitHub analysis, document parsing, browser automation, secure code execution, and forum parsing, enabling LLMs to perform a wide range of external tasks through a single backend.

Capacities MCP Server

Provides seamless integration with Capacities knowledge management system, allowing Claude to list spaces, retrieve space information, search content, save weblinks, and add content to daily notes.

RepoWeaver

MCP server that builds a local code intelligence layer, letting AI agents explore call graphs, blast radius, and source slices via a single tool without external APIs.

mcp-server-zenn: Unofficial MCP server for Zenn (

镜子 (jìng zi)

Mailing Manager MCP

Enables AI assistants to manage multiple email accounts with secure credentials, local full-text search, thread-aware replies, and automation.

Ultrahuman MCP Server

Enables fetching health and fitness metrics from the Ultrahuman API, including heart rate, sleep, steps, temperature, and HRV data.

swiftadopt-mcp

An MCP server that helps developers migrate Swift projects to Apple's 2026 platforms by adopting new frameworks and best practices from WWDC 2026.

jq-docs-mcp

MCP server that provides AI with documentation for 221 JointQuant API functions and 2,479 data table fields, enabling accurate code generation without hallucination.

book-recommendations

Enables AI agents to get book recommendations by topic or mood, discover serendipitous blind-date picks from first sentences, and access free public-domain classics with read-now availability, all with no API keys required.

nano-pay

Self-custodied Nano wallet + x402 payment client and merchant server for AI agents, enabling micropayments, on-ledger settlement, and paid endpoints.

pilot-mcp

An MCP server that gives agents access to a network of 435 specialist agents and peer-to-peer A2A messaging, enabling keyless, real-time data queries and direct communication with other agents.

Understand-Anything MCP Server

Bridges codebase structural analysis, architectural rules, and CI/CD validation with MCP clients, enabling LLMs to check blast radius and prevent breaking changes.

Hashnode MCP Server v2.0

Enables AI assistants to publish, update, and manage Hashnode blog articles, with support for tags, cover images, and publication management.

ThingsBoard Lighting MCP Server

An MCP server that lets Claude read and switch the 3 lights in the innovation room through ThingsBoard, using natural language.

QA MCP Server

An AI-powered QA automation server that integrates Jira, GitHub, Jenkins, AWS, and Webex into a unified interface for QA engineers.

MCP Work History Server

A Model Context Protocol server that enables AI tools to automatically log their activities with detailed metrics like timestamps, token usage, and costs into daily markdown worklog files.

spectra-mcp

An MCP server that provides LLMs with a fingerprint-randomized Firefox browser for web browsing, clicking, typing, and taking screenshots, using invisible_playwright.

mcp-for-spotlight

An MCP server that exposes macOS Spotlight search as tools, wrapping mdfind and mdls to provide full-text and metadata file search across the system.

MCP Translation Text

Provides text translation capabilities powered by NiuTrans API with support for 455+ languages. Includes translation tools and language catalog resources for seamless integration with MCP clients.