دليل خوادم MCP
53,568 خادم MCP تربط مساعدي الذكاء الاصطناعي بالأدوات والبيانات، من سجل MCP الرسمي والقوائم المجتمعية، وتُحدَّث كل ساعة.
- 16 فئة
- 33,917 خادم بعيد
- يُحدَّث كل ساعة
Bonafido: Business Domain Verification APIio.github.CyberMax-tools/domain-verify
Bonafido: is a domain a real business site? Verdict, trust score, risk flags.
Bonafido: Business Domain Verification APIio.github.shawmena-dotcom/domain-verify
Bonafido: is a domain a real business site? Verdict, trust score, risk flags.
ProofGraph (Antigravity MCP)io.github.AI-BuildInfra/proof-graph
Evidence-first entity and knowledge graph MCP server for AI agents to verify claims.
Ternivo Connectio.github.homesteadliving/ternivo-connect
Agent-ready social delivery with preflight, verification, retries, diagnostics, and audit controls.
MCP Cross-Model Delegationio.github.Jostophe-021/mcp-cross-model-delegation
Local MCP framework for bounded cross-model delegation, routing and evidence verification.
Creator Desk Agent Supervisorio.github.creatordeskai-prog/creator-desk-agent-supervisor
Agent completion verification with defects, corrections, and evidence receipts.
Trade Complianceio.github.pipeworx-io/trade-compliance
Trade Compliance MCP — the two questions an importer asks that the tariff
Httpcatio.github.pipeworx-io/httpcat
HTTP Cat MCP — wraps http.cat (free, no auth)
Dicebeario.github.pipeworx-io/dicebear
DiceBear MCP — wraps DiceBear Avatar API v7 (free, no auth)
GoAI Moat Supplier Sourcing & QCcom.goaimoat/supplier-sourcing
Supplier scoring, AQL sampling plans and factory audit checklists for cross-border sourcing.
GoAI Moat Claim Verifiercom.goaimoat/claim-verifier
Verify business claims and audit text for unsourced data.
Tieruxcom.tierux/mcp
Server-side purchase verification and entitlements for Google Play and Apple App Store over MCP.
Bug Bounty Finder - HackerOne + Bugcrowd + security.txtio.github.AnshumanAtrey/bug-bounty-finder
Bug Bounty Finder - HackerOne + Bugcrowd + security.txt
Aziel Runtimeio.github.AzielEliab/aziel-runtime
Governed MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.
API.market MCP Gatewayio.github.Noveum/api-market-gateway
Connect AI agents to 580+ APIs with OAuth or API-key auth. Hosted gateway; API pricing varies.
movahedi.ca Privacy Dataca.movahedi/privacy
Canadian privacy enforcement, glossary, and Quebec Law 25 guidance for AI agents.
goliveio.github.myanptl/golive-mcp
Check a site before you share it: link previews, SPA refresh 404s, noindex, security headers.
housestyleio.github.myanptl/housestyle-mcp
Audits CSS for the generic AI-built look, then fixes it: fonts, contrast, palettes, type scales.
SaaSCityio.saascity/saascity
Audit your site, pick from 1,600+ launch directories by DR and link type, and list on SaaSCity.
AdvisorPPCcom.advisorppc/advisorppc
Connect authorized ad accounts to AI assistants for audits, reporting, and approval-gated changes.
CVElens Vulnerability Intelligencecom.cvelens/cvelens
CVE triage in one call: NVD, CVSS, CISA KEV, EPSS, public exploits and an explained risk score.
Termixio.github.sujirodev/termix-mcp
Manage hosts, snippets, dashboard, metrics and audit of a self-hosted Termix (SSH/RDP/VNC manager)
Teetrackit.teetrack/teetrack
Privacy-first time tracking for freelancers. EU-hosted, with an MCP server for AI assistants.
Agent Guestbookcom.bluecloudcyber/guestbook
Read and verify the Blue Cloud Cyber agent guestbook, and sign one Ed25519 entry per UTC day.
EverThreadio.github.PB-Digital-LLC/everthread
Plain-English website security check for agents: certificate, headers, scripts, forms, spam.
Hands for Agentscom.handsforagents/hands
Human-operated physical world in the EU: make, assemble, measure, verify, ship.
SecScanus.secscan/secscan
Scan, monitor and fix a live web app from your editor: graded security reports with fix prompts.
DidWorksh.didwork/didwork
Verify that an agent's claimed outcome actually happened, using independently gathered evidence
Routavocom.routavo/routavo
Any API, four tools: discover, call with routing and signed receipts, verify, dispute.
MCP Server Auth Templateio.github.brunovicco/mcp-server-auth-template
OAuth 2.1/OIDC resource-server reference for secure MCP authorization
MCP Blast-Radius Auditorio.github.aos-standard/mcp-blast-radius
Static blast-radius audit for MCP servers before agent install. Manifest optional.
Jev MCP Servergithub.com/wangkuangkuang/jev-mcp-server
Typed judgments from TypeSafe Jev: calibrated choice and score questions, A/B comparison, claim-vs-evidence verification and batch classification.
MONEYGRIDio.github.scimo2021/moneygrid-gridwatch
Four x402 tools: endpoint checks, extraction, evidence verification, domain intelligence.
Since.devio.github.Since-dev/mcp
Watch dependencies, verify facts, inspect coverage, and catch up on changes with durable cursors.
AGT agent namescom.agtnames/agt
Resolve, verify and discover .agt agent names: owner, records, signed manifest, endpoints.
Sigasi Magic HDLcom.sigasi/magic-hdl
Analyze and verify Verilog, SystemVerilog, and VHDL projects from AI agents over MCP.
Cambridge China Bridge — China sourcinguk.co.camchinabridge/sourcing
UK import duty, landed cost, anti-dumping and compliance checks for China-sourced goods.
RealAgent MCPio.github.RedDateTech/realagent-mcp
AI agent real-name identity: SM2 keypair, QR real-name link, SD-JWT VP generate/verify.
FacilityProofcom.davisvillelabs/facilityproof
Source-reconciled U.S. environmental facility compliance evidence for AI agents.
mcp-armorio.studiomeyer/armor
Security sidecar for MCP servers: 11 read-only control-plane tools for prompt-injection checks.
Intakra Public Signal Reviewcom.intakra/buying-signal-review
Score supplied buying-signal evidence and prepare review-only why-now briefs. Read-only, no auth.
Soxoa Automation Plannercom.soxoa/automation-planning
Estimate illustrative automation ROI and rank recurring workflows to automate. Read-only, no auth.
Jsmonsh.jsmon/mcp
Discover exposed assets, leaked secrets, APIs & client-side vulns across your attack surface
MCPSentinelio.github.gentaArnezzi/mcpsentinel
Precision-first security scanning for Model Context Protocol servers.
Verityio.github.veritylabsai/verity
Cited product-compliance ground truth for AI agents. Never generates; always cites.
referencesource.orgio.github.joelp22-maker/referencesource
Verified reference data; each record carries its source URL and quote. verify_quote checks claims.
Agent Experience Network Live Preflightio.github.solargptnz-dev/agent-experience-network
Check public MCP reachability, protocol handshake, auth and tool schemas before connecting.
Klarionio.github.0x1Adi/klarion
Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.
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.