دليل خوادم MCP
53,420 خادم MCP تربط مساعدي الذكاء الاصطناعي بالأدوات والبيانات، من سجل MCP الرسمي والقوائم المجتمعية، وتُحدَّث كل ساعة.
- 16 فئة
- 33,798 خادم بعيد
- يُحدَّث كل ساعة
HumanFncom.humanfn/humanfn
Qualified human outcomes for AI agents: attorney review of SaaS Terms/Privacy, on-site checks.
Siigo Latamcom.siigolatam/siigo
Catálogo, precios, artículos, compliance y datos de Siigo por país, en vivo para agentes de IA.
Spooliscom.spoolis/mcp
Verify AI work against criteria and get signed receipts. From Spoolis, guarantees for AI work.
GBU Complianceapp.rowb.gbu-compliance/assessment
German Gefaehrdungsbeurteilung: assess against the ArbSchG s5(3) checklist and build the s6 record.
TradeStar Insidercom.tradestarinsider/edgar-insider-signals
Filing-verified SEC EDGAR insider (Form 4), 13D, 13F & 8-K data, no sign-in. Verify any claim.
Agent deliverable verification: acceptance criteria vs evidencecom.nodcheck/nodcheck
Verify deliverables before shipping: acceptance criteria checked against evidence; signed record.
AllyOtter Litecom.allyotter/allyotter-lite
Get a digital product ready for affiliate networks: requirements, sales-page audit, checklists.
BUMITai.bumit/verify-business
Swiss business verification with per-check source provenance and evidence freshness.
Creator Desk Commerce Completion Verifyio.github.creatordeskai-prog/x402-completion-verify
Evidence-based commerce completion checks for agents. x402 paid calls and free standard metadata.
Csl Coregithub.com/Chimera-Protocol/csl-core
Deterministic AI safety policy engine with Z3 formal verification: write, verify and enforce machine-verifiable constraints for AI agents.
Lattice: CVE, MITRE ATT&CK and detection graph for security agentsio.namiq/lattice
CVE, KEV, MITRE ATT&CK, CWE and detection graph for AI agents; every link names its source.
Kaminari Adio.github.kaminari-ad/mcp
Real-device ad verification: malvertising and cloaking scans, AI policies, alerts, webhooks.
Prop Firm Rules (FloorGuard)io.github.kburrus64-max/prop-firm-rules
Sourced prop-firm daily-loss and max-drawdown rules and a drawdown-room checker. Read-only, no auth.
Emilia Protocolio.github.emiliaprotocol/mcp-server
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
OokCiteio.github.TurtleTech-ehf/ookcite-mcp
Catch fabricated citations: verify DOIs/ISBNs and format them in 2900+ CSL styles.
AgentsJunctionio.github.JakubTrousil/agentsjunction
Discover MCP servers and A2A agents; verify, message, post, follow, react, and receive webhooks.
Datoka APIdev.workers.bhazarstudio.datoka-api/api
Signed API declarations for agent handoffs. Free demo and verification; receipts cost 0.002 USDC.
Datoka Agentdev.workers.bhazarstudio.datoka-agent/agent
Signed agent execution declarations. Free verification; issuance 0.002 USDC via x402 on Base.
CWI MCP Servercom.cumulativeweb/cwi-mcp-server
Read-only MCP server: CWI Gear Ledger reads, deterministic trust scoring, NEEDLE DROP verification.
Chart Color Auditio.github.socraticstatic/chart-color-audit
CI-friendly accessibility audit for chart color palettes: WCAG contrast, CVD simulation, OKLab ΔE.
Chart Color Systemio.github.socraticstatic/chart-color-system
Solve, audit and simulate colorblind-safe chart palettes. WCAG contrast, OKLab ΔE. Read-only.
HumanEndpointau.humanendpoint/humanendpoint
Human-only capabilities for AI agents: ground truth, verification, judgement and real-world action.
FeeFighterio.github.everyai-com/fee-fighter
Audit junk fees, project annual costs and draft dispute letters. Free.
Entrolyio.github.juyterman1000/entroly
Context Assurance for AI agents: context engineering, AI cost optimization, verification.
n8n MCP Communityio.github.drzamarian/n8n-mcp-community
A security-focused MCP server for self-hosted n8n Community Edition.
中国 AI 合规与备案（条文级自查）cn.savantcat/ai-compliance
生成式AI备案、AI生成内容标识、深度合成、算法备案：条文级问答 + 按条号取法规原文 + 应办清单（中文）
handoff — agent swarm coordinationio.github.34r7h/handoff
Agent swarm coordination: find funded work, form teams, run tasks, message E2E, get paid on verify.
Lumaion Continuityapp.lumaion/continuity
Agent continuity: live continuity index, self-test contract, offline Continuity Proof verification.
CodeInspectusio.github.Synvoya/codeinspectus
Local-first MCP security scanner and CLI for AI-generated applications.
ALEX Evidence Verifyio.github.Alex-Proof/alex-evidence-verify-mcp
Verify signed ALEX Evidence Packages. Fails closed on signature or schema errors.
Jacobianio.github.morluto/jacobian
Executable mathematics and independent verification for AI agents.
Faxivo Newscom.faxivo/news
News written and read by AI agents. Every article carries a verification status.
desenmascara.meme.desenmascara/desenmascara
Is this website a scam? Dated, sourced fraud assessments of domains. Free, read-only, no key.
Ailooplibrary MCPgithub.com/paultaki/ailooplibrary-mcp
Read-only AI Loop Library catalog of bounded agent work loops: pick one for a goal and render a run protocol with verification, stop conditions and budgets.
Web Evidenceio.github.impanyu/web-evidence
Paid claim verification with cited web evidence, source provenance, snapshots, and hashes.
Trentai.trent/trent
Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
Burs-IAio.github.soyeladice-svg/burs-ia
Public MCP for agent verification, work discovery and governed interoperability.
Shipstoresgithub.com/FidelisMM/shipstores
Ship iOS and Android apps end to end: App Store Connect, Google Play Console and Expo EAS builds, listings, screenshots, privacy labels, review submission an...
FAOSTAT MCPio.github.berba-q/faostat-mcp
FAOSTAT data for 245 countries: crops, trade, food security, and emissions via 23 MCP tools.
MAC Address Lookupcom.jasontally.mac/mcp
Find the organization behind a MAC address or OUI prefix in the IEEE registries. No auth, no key.
Azertia Relaytop.vibecoderau.azertia/relay
A public relay where AI instances read traces left by others and may leave one. No auth.
人生增值（zengzhi.life）MCPlife.zengzhi/zengzhi
人生增值 ZengZhi — 个人数字资产审计/撮合平台 (digital-asset audit/matchmaking): 公开 tools 免 Key, 个人数据需 Bearer zzk_.
unflagdomain: website blacklist removalcom.unflagdomain/website-blacklist-removal
Website flagged by security vendors? Free scan, then we send the removal requests for you (paid).
Japan External Executionio.github.furoito/japan-physical-capability
Manual-review external execution in Japan for AI agents: human tasks, logistics, and verification.
Presend MCP Serverio.github.presendapp/presend-mcp
Before an AI agent installs an npm/PyPI package: typosquat, vulnerability and existence checks.
AI Agents Pitstopcom.ai-agents-pitstop/pitstop
Human approvals, autonomy limits and a chained audit log for the AI agents of service firms.
skanfirmy.plio.github.bartosz-kuc/skanfirmy
Verify Polish companies by NIP/KRS/REGON + EU VAT (VIES). 14 MCP tools (9 no-key).
remirror (返照） — psyche audits for AI agentsio.github.OntoDistro/remirror
Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.
من سجل MCP الرسمي. الإدراج ليس توصية: راجع شيفرة الخادم وصلاحياته قبل منحه الوصول إلى بياناتك. آخر مزامنة ٢٨/١٠/٢٠٢٦.
الأسئلة الشائعة
ما هو MCP؟
بروتوكول سياق النموذج معيار مفتوح يتيح لمساعد ذكاء اصطناعي (Claude أو ChatGPT أو Cursor أو وكيل) استدعاء أدوات خارجية وقراءة بيانات خارجية عبر «خادم». الخادم البعيد رابط تضيفه إلى عميلك، والمحلي يعمل على حاسوبك من حزمة (npm أو PyPI أو Docker).
كيف أضيف خادم MCP إلى Claude أو Cursor؟
افتح صفحة الخادم هنا وانسخ كتلة الإعدادات إلى ملف إعدادات MCP في عميلك ثم أعد تشغيله. الخوادم البعيدة تحتاج الرابط فقط، والمحلية تتطلب Node (npx) أو Python (uvx) أو Docker.
هل هذه الخوادم آمنة؟
يمكن لأي شخص النشر في السجل. يستطيع الخادم قراءة ما تمنحه الوصول إليه والتصرف نيابةً عنك، لذا فضّل الخوادم ذات الشيفرة العامة من ناشر تعرفه، وامنح أقل صلاحيات ممكنة.