发现优秀的 MCP 服务器
通过 MCP 服务器扩展您的代理能力,拥有 86,267 个能力。
postgres-mcp
A Python MCP server that provides PostgreSQL database connectivity for Text-to-SQL workflows, enabling AI agents to explore schemas and execute parameterized SQL queries across multiple data marts.
Memorium
Enables AI assistants to have persistent long-term memory by automatically storing and retrieving important information via MCP tools.
DaVinci-Resolve-MCP
A stdio MCP server for DaVinci Resolve on macOS, enabling project control, timeline navigation, frame capture, grade application, and validation through the official Resolve scripting API.
Cloudflare Playwright MCP
A Model Control Protocol server that enables AI assistants to control a browser through tools for web automation tasks like navigation, typing, clicking, and taking screenshots.
Signal8 MCP Server
Provides AI agents with direct access to SEC filing intelligence, company fundamentals, dilution risk scoring, and cross-company analytics for financial research.
whisper-mcp
MCP server that provides a transcribe_audio tool to convert voice messages from channels into text using OpenAI Whisper, enabling Claude Code to process audio attachments.
Self-hosted AI starter kit (by the n8n team)
Okay, here's a translation of "pydantic agent workflow using mcp servers to test out advanced retrieval of linked data" into Chinese, along with some nuances and considerations: **Option 1 (More Literal, Emphasizing Technical Aspects):** 使用 Pydantic 代理工作流,通过 MCP 服务器测试链接数据的高级检索 * **使用 (shǐyòng):** Using, employing * **Pydantic 代理工作流 (Pydantic dàilǐ gōngzuòliú):** Pydantic agent workflow (This is a direct transliteration, common in technical contexts) * **通过 (tōngguò):** Through, via * **MCP 服务器 (MCP fúwùqì):** MCP servers (Again, direct transliteration) * **测试 (cèshì):** To test, testing * **链接数据 (liànjiē shùjù):** Linked data * **高级检索 (gāojí jiǎnsuǒ):** Advanced retrieval **Option 2 (Slightly More Natural, Still Technical):** 利用 Pydantic 代理工作流,借助 MCP 服务器探索链接数据的高级检索 * **利用 (lìyòng):** Utilizing, leveraging * **借助 (jièzhù):** With the help of, by means of * **探索 (tànsuǒ):** To explore, to investigate **Option 3 (More Descriptive, Less Literal):** 构建基于 Pydantic 的代理工作流,并使用 MCP 服务器来验证链接数据的高级检索能力 * **构建 (gòujiàn):** To build, to construct * **基于 (jīyú):** Based on * **验证 (yànzhèng):** To verify, to validate * **能力 (nénglì):** Capability, ability **Explanation of Choices and Considerations:** * **"Pydantic agent workflow" and "MCP servers":** In technical contexts, it's often acceptable (and even preferred) to directly transliterate these terms. If the audience is familiar with these technologies, transliteration is the clearest option. If you *need* to explain them, you could add a brief explanation in parentheses after the transliteration the first time they appear. * **"Test out":** The English phrase "test out" can be translated in several ways. "测试 (cèshì)" is the most direct translation of "test." "探索 (tànsuǒ)" implies a more exploratory testing process. "验证 (yànzhèng)" implies a more formal validation of capabilities. * **"Advanced retrieval of linked data":** "高级检索 (gāojí jiǎnsuǒ)" is a good, general translation of "advanced retrieval." The key is to ensure the audience understands what "linked data" means. **Which option is best depends on the context:** * **For a highly technical audience already familiar with Pydantic and MCP:** Option 1 is likely the best. * **For a slightly less technical audience, or if you want to emphasize the exploratory nature of the testing:** Option 2 might be better. * **If you want to emphasize the building and validation aspects:** Option 3 is a good choice. **Recommendation:** I would recommend **Option 1** or **Option 2** as a starting point, and then adjust based on your specific audience and the purpose of the translation. If you provide more context about where this translation will be used, I can refine it further.
Cursor Model Context Protocol (MCP) Example
这个仓库包含模型上下文协议(MCP)服务器的示例实现,这些服务器可以与 Cursor IDE 一起使用,通过自定义工具和数据源来增强 AI 功能。
linkinator-mcp
A Model Context Protocol (MCP) server that provides link checking capabilities using linkinator, enabling AI assistants to scan webpages and local files for broken links.
mcp-server-hcp-terraform
用于与 HCP Terraform 协同工作的 MCP 服务器
MCP Server Boilerplate
A minimal, extensible template for building Python-based MCP servers supporting STDIO and SSE transports with VS Code integration.
Tech News Update Agent
A FastAPI backend that integrates with ElevenLabs MCP to create an AI agent capable of making outbound calls and delivering friendly, jargon-free tech news updates.
OpsNow MCP Cost Server
mcp-kindle
Read-only MCP server for accessing local Kindle library data, exposing tools to query profile, health, and book metadata.
Sentinel
A safe, allowlisted MCP server that lets AI agents run only a tiny set of harmless tools (echo, datetime, hash, dig, GET-only curl, whois, status checks) against explicitly allowed hosts, with sanitization, rate limiting, timeouts, and full audit logging.
@us-all/dbt-mcp
A read-only MCP server that exposes dbt project artifacts and data quality result tables (BigQuery/Postgres) to LLM clients, enabling deep introspection, run-history analysis, source freshness, test coverage, and lineage walks.
GitHub GraphQL API MCP
Enables querying and exploring the GitHub GraphQL API schema and executing optimized GraphQL queries to retrieve precise GitHub data (repositories, issues, PRs, users) with reduced token consumption.
Semantic Perch Intelligence MCP
MCP server for Cloudflare D1 database introspection, providing schema analysis, relationship extraction, validation, and optimization suggestions via Semantic Intent patterns.
Jina Free MCP
A Managed Component Provider that enables fetching webpage content using Jina AI's reader service.
Haypile
Hybrid search over your local documents, with file and page citations. One binary, fully local.
gencc-link
MCP server that provides tools to query harmonized gene-disease validity data from the Gene Curation Coalition, supporting consensus and conflict detection for gene-disease assertions.
MCP2Browser
Provides browser automation capabilities through HTTP, allowing AI assistants to navigate web pages and inspect content using Playwright-powered tools for opening URLs and retrieving page information.
agenticpay
agenticpay lets MCP server developers monetize tools via per-call USDC micropayments on Solana, using the x402 protocol. Each tool declares a price; agents pay via signed Solana transactions; settlement happens on-chain in ~1.5–2 seconds.
SurfRank MCP Server
Enables AI assistants to access SurfRank's AI visibility analytics platform through 24 tools. It allows agents to run AI-visibility reports, research keywords, track competitors, and manage projects directly from chat interfaces.
clickup-mcp
A Model Context Protocol (MCP) server exposing the full ClickUp REST API v2 as MCP tools, enabling natural language management of ClickUp workspaces, spaces, folders, lists, tasks, custom fields, comments, goals, views, webhooks, and time tracking via any MCP-compatible client like Claude Desktop or Cursor.
wgea-mcp
MCP server for the Workplace Gender Equality Agency (WGEA) per-employer dataset. Plain-English access to workforce composition, manager movements, pay-gap actions, parental leave, flexible work, and harm-prevention policies for every Australian employer with 100+ employees. CC-BY 3.0 AU.
agentmem
Governed memory for coding agents with trust lifecycle, conflict detection, staleness tracking, and health scoring. SQLite + FTS5, zero infrastructure. Works with Claude Code, Cursor, Codex, Windsurf.
meetey
Local-first meeting capture and transcription for Claude Code. Records audio from meeting apps, transcribes locally with whisper.cpp, and produces structured notes via Claude.
NeoVimMCP
Enables AI clients to interact with Neovim buffers via MCP tools, providing buffer and cursor context.
subnoto
Subnoto - Electronic Signature MCP server allows to send, receive and sign electronic documents with legally binding signatures. It connects to a confidential computing environment to ensure confidentiality of exchanged documents.