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。
jira-service-desk-mcp
Connects AI assistants to Jira Service Management instances, providing 40 tools for managing service desks, requests, comments, customers, organizations, queues, SLA, approvals, and attachments.
AI Loop Library MCP
Provides coding agents with 63+ bounded, verifiable work loops, enabling goal-driven loop selection and executable protocol generation via MCP tools.
cimc-mcp
An MCP server for managing standalone Cisco C-Series rack servers through the Cisco Integrated Management Controller (CIMC) XML API. It provides 16 tools for server lifecycle management, including power control, hardware health monitoring, and BIOS configuration.
MCP Context Graph
A self-contained, in-memory graph database for AI Agents. Provides semantic code understanding through the Model Context Protocol (MCP).
Renderly MCP
Enables AI agents to capture clean web screenshots and extract main article content from any web page, with automatic removal of cookie banners, ads, and boilerplate.
Base MCP Server
Enables AI applications to interact with the Base blockchain network and Coinbase API, supporting wallet operations, smart contract deployment, token transfers, NFT management, DeFi lending through Morpho vaults, and onramp functionality.
candlestick-chart-mcp
Renders OHLCV data as candlestick chart PNGs and returns inline images. It is a pure renderer with no network access, allowing models to view charts generated from provided data.
BioMCP
Read-only biomedical MCP server connecting PubMed, ClinicalTrials.gov, ClinVar, gnomAD, OncoKB, Reactome, KEGG, UniProt, PharmGKB, CPIC, OpenFDA, Monarch Initiative, GWAS Catalog, and more. One command grammar for all biomedical entities — genes, variants, diseases, drugs, trials, articles, phenotypes, pathways, proteins, diagnostics, and adverse events. 27 tools. Apache-2.0 license.
langfuse-mcp-java
Query Langfuse traces, schema and datasets, scores and metrics, debug exceptions, analyze sessions, and manage prompts. Full observability toolkit for LLM applications.
Personal Cronometer MCP
Enables MCP clients like Codex and Claude Code to securely read and manage a personal Cronometer account, including food logs, nutrient summaries with missing-data awareness, food search, biometrics, and export analysis.
Tether MD
Enables anchored comments in Markdown files that AI agents can propose changes for, with human approval before application, all managed via an MCP server.
mcptime
Here's the translation of "Simple MCP server to return the current time" into Chinese, along with a few options depending on the nuance you want to convey: **Option 1 (Most straightforward):** * **简单的 MCP 服务器,返回当前时间** * (Jiǎndān de MCP fúwùqì, fǎnhuí dāngqián shíjiān) This is a direct translation and is generally suitable. **Option 2 (More technical, emphasizing the function):** * **一个简单的 MCP 服务器,用于返回当前时间** * (Yī gè jiǎndān de MCP fúwùqì, yòng yú fǎnhuí dāngqián shíjiān) This emphasizes the *purpose* of the server. "用于" (yòng yú) means "used for" or "for the purpose of." **Option 3 (Slightly more formal):** * **一个简单的 MCP 服务器,用于提供当前时间** * (Yī gè jiǎndān de MCP fúwùqì, yòng yú tígōng dāngqián shíjiān) This uses "提供" (tígōng), which means "to provide" or "to offer." It's a bit more formal than "返回" (fǎnhuí). **Breakdown of the words:** * **简单 (jiǎndān):** Simple * **的 (de):** A possessive particle (like "of" or "'s" in English) * **MCP 服务器 (MCP fúwùqì):** MCP server (assuming MCP is an acronym you want to keep as is) * **一个 (yī gè):** A, one * **用于 (yòng yú):** Used for, for the purpose of * **返回 (fǎnhuí):** Return (as in a function returning a value) * **提供 (tígōng):** Provide, offer * **当前 (dāngqián):** Current * **时间 (shíjiān):** Time Choose the option that best fits the context of your communication. If you're just quickly describing the server, Option 1 is perfectly fine. If you're writing documentation or a more formal description, Option 2 or 3 might be better.
codabench-mcp
MCP server for Codabench REST API that enables AI agents to drive a full participant ML-benchmark workflow: discover competitions, download data, submit, poll, and read leaderboards.
LINDAS MCP Server
Enables LLMs to query structured statistical data from the Swiss Federal Archives' Linked Data platform (LINDAS) by translating natural language questions into SPARQL queries against RDF data cubes.
Coinranking1 MCP Server
Provides access to the Coinranking1 API for retrieving real-time cryptocurrency data, including trending coins, blockchain details, and global market statistics. It enables users to search for digital assets and track historical market capitalization and trading volumes.
claude-chrome
Enables browser automation via Chrome, allowing navigation, clicking, typing, screenshotting, and replayable flows for web tasks.
Igloo MCP
Enables AI assistants to interact with Snowflake databases through SQL queries, table previews, and metadata operations. Features built-in safety checks that block destructive operations and intelligent error handling optimized for AI workflows.
meican-mcp
美餐MCP服务器,支持查询餐次、餐厅、菜单和订单,以及下单和取消订单操作。
procurement-mailer-mcp
Enables an SAP Joule agent to read and send email from a scoped Microsoft Exchange mailbox via MCP tools, translating tool calls into Microsoft Graph requests.
jira-issue-context-mcp
Read-only MCP server that fetches a single Jira issue by key and returns its title, description, comments, attachment summary, and image attachments.
provgraf-mcp
Read-only MCP server exposing a W3C PROV knowledge graph of verified facts with provenance, enabling AI agents to list, search, and check facts while enforcing that writes remain CLI-only.
Agent Guild
The trust and settlement layer for AI agents: discover the safest agent for a job, vet a counterparty before delegating, pay safely via escrow, and carry portable Guild-signed reputation. Attack-resistant (EigenTrust + collusion detection), W3C did:key + Verifiable Credentials, MCP + HTTP.
MCP Code Review Server
A code review tool that generates detailed HTML review documents by comparing branches or commits, with author filtering and intelligent analysis.
physbound
PhysBound is a specialized "Physics Linter" for AI that deterministically validates RF and thermodynamic claims against hard physical limits, preventing hallucinations in engineering workflows.
screen-use
Enables AI agents to see, locate UI elements, and operate any Windows desktop app through natural language, using accessibility-tree matching with optional vision-model fallback, plus an autonomous visual loop with introspection and meta-learning.
agent-token-stripper
Enables LLM agents to convert bloated webpages into clean token-dense plain text, stripping HTML, CSS, scripts, and layout elements while reducing context-window costs and supporting x402 micro-pay-based autonomous requests.
AI Pentest MCP Server
An MCP server that turns Kali Linux into an AI-driven penetration testing powerhouse, enabling control of 40+ offensive security tools via natural language.
Routine
An MCP server that allows users to create custom tools on the fly by stitching together actions from multiple MCP tools into reusable routines.
Map Canvas MCP
Enables interactive map display with up to 50 marked places and optional route lines, using a bundled Leaflet UI and OpenStreetMap tiles.
MyMCP
Dynamically converts any OpenAPI v3 specification into a fully-functional Model Context Protocol (MCP) server.