回首頁MCP 伺服器目錄
重點摘要：MCP 伺服器目錄整理官方 MCP Registry 上註冊的伺服器，可用關鍵字、13 種分類與「只看遠端」篩選，每頁 50 筆，可遠端連線的伺服器排在前面，並附安裝套件、遠端網址與原始碼連結。
官方 MCP Registry 上的伺服器，共 46,271 筆。可遠端連線的伺服器排在前面。
| 伺服器 | 說明 | 連線 | 分類 |
|---|---|---|---|
| maidr io.github.xability/maidr-mcp | Accessible maidr charts in ChatGPT and Claude, explored by sound, braille and screen reader | pypioci | 開發工具 |
| Quorus io.github.Quorus-dev/quorus | Shared rooms, messages, file locks and task claims for AI coding agents from any vendor. | pypi | 檔案與文件開發工具AI 與模型 |
| ENT ONE (Edifice) io.github.edouard-claude/ent1-mcp | ENT ONE school workspace for parents: teacher messaging, liaison book, homework, news. | oci | 開發工具 |
| io.github.MadeByFYI/madeby io.github.MadeByFYI/madeby | Disclose AI authorship of code per the ACO standard — tools for AI coding agents. | npm | 開發工具AI 與模型資安 |
| Claimidx io.github.claimidx/claimidx | Prior art for AI agents. init wires DID/MCP; share-yes to commons (ask alone does not). | pypi | 開發工具AI 與模型 |
| Beadhive io.github.beadhive/beadhive | Manage cross-repository beads work, hive status, and Beadhive workflows through bh-mcp. | pypi | 開發工具電商與行銷 |
| Nido — Fast, Simple VM Sandboxes for AI Agents (Temporary & Persistent) io.github.Josepavese/nido | Manage temporary or persistent Linux VMs (QEMU/KVM). Designed for AI agents and automation. | mcpb | 開發工具設計與多媒體AI 與模型 |
| vivac io.github.JAAvila-Of/vivac | Provenance tree for coding agents: where you are, why, and what was already decided | cargo | 開發工具AI 與模型 |
| Google Search Console Connector io.github.malaysherasia-ai/google-search-console-connector | Google Search Console: search analytics, CSV reports, URL inspection, sitemaps, site verification. | npm | 搜尋開發工具地圖與旅遊電商與行銷 |
| MCP Hangar io.mcp-hangar/hangar | Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT. | pypi | |
| jevmem io.github.Avinash-jetwani/jevmem | Automatic project memory for Claude Code and Cursor; Codex and Claude Desktop over MCP. | npm | 開發工具AI 與模型 |
| io.github.JoblessJoe/localize io.github.JoblessJoe/localize | Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code. | npm | 檔案與文件搜尋開發工具AI 與模型電商與行銷 |
| io.github.qso-graph/n1mm-mcp io.github.qso-graph/n1mm-mcp | N1MM Logger+ MCP server. Live contest state: QSOs, bandmap, score, rate, multipliers. | pypi | 開發工具地圖與旅遊 |
| Aileron Journal io.github.aileron-sh/aileron | Read-only queries over Aileron audit journals: verify integrity, search recorded tool calls | pypi | 搜尋開發工具 |
| GridPath io.github.pixelsmasher13/gridpath | Edit real .xlsx files with your agent: live formulas, and you review every change before it saves. | npm | 檔案與文件開發工具AI 與模型 |
| io.github.hmamut39/tewip io.github.hmamut39/tewip | Proves software work: triages failing tests, checks whether a test can fail, and reads migrations. | npm | 開發工具電商與行銷 |
| io.github.qso-graph/omiss-mcp io.github.qso-graph/omiss-mcp | OMISS MCP server. Net schedule, nets on the air, members, check-in history, awards. | pypi | 開發工具 |
| io.github.faze79/wpf-visual-tree io.github.faze79/wpf-visual-tree | Inspect and drive WPF apps: trees, bindings, screenshots, mouse dragging and touch gestures. | nuget | 檔案與文件開發工具AI 與模型 |
| opendrs io.github.error-path/opendrs | PR blast radius and 0-1 risk score from git history, so low-risk PRs can be auto-approved. | npm | 開發工具 |
| ReversePort io.github.laaielichter/reverseport | Reverse engineer anything. Port it anywhere. One MCP server for coding agents. | npm | 開發工具AI 與模型 |
| Cost Guard MCP io.github.mcpsmiths/cost-guard-mcp | Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks | pypi | 資料庫開發工具地圖與旅遊AI 與模型 |
| Ba-Zi.ai Chinese Astrology io.github.xlw-pro/chinese-astrology-skill | BaZi Four Pillars charts, bone weight fortune (称骨) and Chinese almanac (黄历) by Ba-Zi.ai. | npm | 開發工具 |
| XRechnung Validator io.github.wenboteng/xrechnung-validator | Validate one XRechnung or ZUGFeRD file with the free checkxrechnung.com API. | npm | 檔案與文件開發工具 |
| io.github.WSattazahn/caveat-lang io.github.WSattazahn/caveat-lang | Authoring bridge for Caveat: validate, check and test programs; explain decisions; find dependents. | npm | 開發工具資安 |
| indexio io.github.IOServicesLabs/indexio | Code search, symbols and call graph for AI coding agents. Answers in milliseconds. | npmpypi | 搜尋開發工具AI 與模型 |
| io.github.Sanoy24/safe-fetch io.github.Sanoy24/safe-fetch | MCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks. | npm | 開發工具 |
| Monte-Neo strategy verifier io.github.NeoZorK/monte-neo | Verify trading-strategy backtests: look-ahead probes, trading costs, Deflated Sharpe, walk-forward. | pypi | 開發工具財經與加密 |
| io.github.brac/particlr-mcp io.github.brac/particlr-mcp | Agents author particlr .prt particle effects headlessly: validate, simulate, render to PNG, patch. | npm | 開發工具AI 與模型資安 |
| Hronaut Browser MCP io.github.hronaut/hronaut | Control visible, persistent Hronaut browser workspaces through a local MCP connection. | mcpb | 瀏覽器與爬蟲開發工具 |
| ops-brain io.github.TheK3nsai/ops-brain | Self-hosted team bus for AI agents: cross-machine handoffs, check-in, and shared gotchas. | oci | 開發工具AI 與模型 |
| io.github.gxc/gaussdb-ro-mcp io.github.gxc/gaussdb-ro-mcp | Read-only MCP server for Huawei GaussDB (centralized & distributed), built for coding agents. | 開發工具AI 與模型 | |
| Agent Comms io.github.ExaDev/agent-comms | Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP | npm | 開發工具AI 與模型 |
| Maiday io.github.35furkan/maiday | Distress signal for AI agents: report where you get stuck on websites and fetch site-owner hints. | npm | 開發工具AI 與模型 |
| io.github.mischuh/canonic io.github.mischuh/canonic | The Open Context Layer for Data Agents | pypi | 開發工具AI 與模型 |
| io.github.ZahiriNatZuke/local-delegate io.github.ZahiriNatZuke/local-delegate | Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota. | pypi | 開發工具AI 與模型 |
| Secret Sentinel io.github.AleBrito124356/mcp-secret-sentinel | Local secret guardrails: scan code, git changes and MCP configs for API keys; redact text | pypi | 開發工具資安 |
| Achromat MOM ai.achromat/mcp-server | Recall and calibrate agent tool calls against verified policy lessons from Achromat MOM. | npm | AI 與模型 |
| Turbo Quant Memory io.github.Lexus2016/turbo-quant-memory | Local-first memory and knowledge graph for coding agents. Compact retrieval, no network. | pypi | 開發工具AI 與模型 |
| io.github.laf-rge/quickbooks-mcp io.github.laf-rge/quickbooks-mcp | MCP server for QuickBooks Online API integration | npm | 開發工具 |
| pkg io.github.tneemo/pkg | Find, install and assemble reusable software builds for coding agents. | npm | 開發工具AI 與模型 |
| PaperType dev.papertype/papertype-mcp | Render Markdown, HTML or invoice/certificate/report templates to PDF files via the PaperType API. | npm | 檔案與文件 |
| SQL MCP Server io.github.nethinwei/sql-mcp-server | Controlled SQL access gateway with policy, cost limits, tenant isolation, and safe tools. | oci | 資料庫開發工具 |
| Fairquery Company Jobs Feed com.getfairquery/company-jobs-feed-mcp | Live jobs from company Greenhouse, Lever and Ashby boards with age, long-open and repost signals. | npm | |
| Fairquery Agent Trust & Data Safety com.getfairquery/agent-trust-mcp | PII/secret redaction, email checks, sanctions screening and OSV vulnerability lookups for AI agents. | npm | 通訊與協作AI 與模型資安 |
| EyalSec io.github.EyalSec/eyalsec-mcp | Read your EyalSec security events, machines, runs and rules from an AI assistant. | pypi | 開發工具資安 |
| GenPark Markdown Mermaid Syntax Lint Healer io.github.alphaparkinc/genpark-markdown-mermaid-syntax-lint-healer-skill | LLM output Mermaid diagram linting, unquoted bracket healing, and syntax normalization engine | mcpb | 檔案與文件開發工具AI 與模型 |
| GenPark SQL Injection AST Taint Analyzer io.github.alphaparkinc/genpark-sql-injection-ast-taint-analyzer-skill | Dynamic SQL AST taint tracking and static vulnerability auditor detecting tautology injections | mcpb | 資料庫開發工具資安 |
| GenPark Adaptive Exponential Backoff with Jitter Retry io.github.alphaparkinc/genpark-adaptive-exponential-backoff-jitter-retry-skill | Full jitter exponential backoff retry scheduling and half-open circuit breaker for LLM APIs | mcpb | 開發工具AI 與模型 |
| GenPark Vector Embedding Cache Deduplication Sentinel io.github.alphaparkinc/genpark-vector-embedding-cache-deduplication-sentinel-skill | High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation | mcpb | 開發工具AI 與模型 |
| GenPark AST Diff Semantic PR Summarizer io.github.alphaparkinc/genpark-ast-diff-semantic-pr-summarizer-skill | Synthesize semantic AST delta trees across git diffs and classify breaking signature changes | mcpb | 開發工具 |
常見問題
MCP 伺服器目錄的資料從哪裡來？
資料來自官方 MCP Registry 的公開 API，本站只整理名稱、說明、版本、遠端網址、安裝套件與原始碼等後設資料，已被標記刪除的伺服器會從目錄移除。
目錄有哪些分類？
共 13 類：資料庫、檔案與文件、瀏覽器與爬蟲、搜尋、開發工具、雲端與基礎設施、通訊與協作、財經與加密、地圖與旅遊、設計與多媒體、AI 與模型、電商與行銷、資安。分類依伺服器名稱與說明的關鍵字自動判定。
「遠端」標籤代表什麼？
代表該伺服器在 Registry 中登記了遠端連線網址，可以直接用網址接到 AI 用戶端，不必在本機安裝套件；沒有遠端網址的則顯示 npm、pypi 等套件來源。
目錄裡的伺服器都安全嗎？
不保證。本站只整理公開後設資料，不代表推薦或安全保證；接入前請自行確認原始碼、發佈者與要求的權限範圍。