دليل خوادم MCP
53,080 خادم MCP تربط مساعدي الذكاء الاصطناعي بالأدوات والبيانات، من سجل MCP الرسمي والقوائم المجتمعية، وتُحدَّث كل ساعة.
- 16 فئة
- 33,580 خادم بعيد
- يُحدَّث كل ساعة
Aetheryaai.aetherya/mcp
Test decisions on a synthetic audience: studies, site audits, copy tests and post simulations.
GenPark Streaming NDJSON & JSONL Schema Validatorio.github.alphaparkinc/genpark-streaming-ndjson-jsonl-schema-validator-skill
Ultra-low-latency incremental line validator with chunk boundary reassembly and schema auditing
GenPark Prompt Injection Canary Leak Sentinelio.github.alphaparkinc/genpark-prompt-injection-canary-leak-sentinel-skill
HMAC-signed zero-width invisible canary token generator and output response leak auditor
zipnative MCP — ZIP creation, inspection, secure extraction & verificationio.github.Nizoka/zipnative-mcp
ZIP MCP server: create, inspect, verify, extract, canonicalize, merge, modify. 15 tools
Suprsonicio.github.O-mega-Enterprise/suprsonic-mcp
One API key, dozens of capabilities for your AI agent. Zero provider auth.
MCP Security Guardio.github.petrovicistefan/mcp-security-guard
Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).
Lanmao Free AI Creditsai.lanmao/free-ai-credits
Hand-verified free AI credits, API trials and free tiers. Read-only, no auth, updated daily.
spintax.net MCP servernet.spintax/mcp
Write, validate, render and analyze spintax templates. Backed by @spintax/core. No auth.
ShopSafe URL verificationau.com.shopsafe/verify
URL risk evidence with scoped OAuth/API keys, capped prepaid costs and up to ten URLs per batch.
rostrumio.github.girishkvs/rostrum
Clean up talk recordings: find redos, retakes and dead air, review every cut, render and verify.
verify-proofio.github.csolomon0704-prog/verify-proof
Verify timestamp proofs offline, anchor hashes through ProofLedger, keep agent run receipts.
chunk-invarianceio.github.ninadphalak/chunk-invariance
Checks whether your streaming redactor leaks a secret split across chunks; writes a pytest for it.
Grideōs Factscom.grideos/facts
Read-only facts about Grideōs from its signed, hash-chained ledger. Verify before you cite.
Own Your Mind DeAI assessmentsai.ownyourmind/oym-substrate
Signed, independent scores and claim checks for decentralised AI projects. Read-only, no auth.
GenPark Complex Financial Formula Audit Validatorio.github.alphaparkinc/genpark-complex-financial-formula-audit-validator-skill
Arithmetic consistency checks and cross-footing validation for financial statements
Diogenes Autonomous Microservice Gatewayio.github.stand-out-of-my-sun/diogenes-gateway
Autonomous AI microservices: 55 dynamic guardrails, contract audits & oracles via L402/x402/MPP.
passmcpcom.sebastienrousseau/passmcp-server
Evaluate an MCP server with passmcp and verify its attestations, from inside the agent. Read-only.
Vaara MCP Serverio.github.vaaraio/vaara-server
Accountable autonomy MCP server: gating, tamper-evident audit for every action
Vaaraio.github.vaaraio/vaara
Accountable autonomy proxy: gating, tamper-evident audit, time anchor for every action
opsgateio.github.polymatx/opsgate
The safety gate between AI agents and your servers: typed, policy-checked, audited ops tools.
Auditon security assessmentsco.auditon/assessments
Read-only access to your Auditon vulnerability scans: findings, endpoints, reports and changes.
Security Headersio.github.basitalisandhu/mcp-security-headers
Fetch a URL's response headers and grade CSP, HSTS, X-Frame-Options and related security headers.
OSV Advisoriesio.github.basitalisandhu/mcp-osv-advisories
Query OSV.dev for known vulnerabilities by package and version, and scan lockfiles in batch.
JWT Toolsio.github.basitalisandhu/mcp-jwt-tools
Decode JWTs without verifying, flag risky algorithms and claims, verify HS256 or RS256 with a key.
STEADYWRK Agentic Readiness Probe, Store Guard and Dispatchapp.steadywrk/mcp-dispatch
Keyless storefront readiness probe linking a Store Guard audit, plus dispatch estimates and quotes.
Landfallio.github.landfall-audit/landfall
Website intelligence for AI agents: landing page audits, business contact details, tracking checks.
Tytoncom.usetyton/tyton
Audit and set up Meta Pixel and the Conversions API from your AI agent.
MCP Auditgithub.com/P4ST4S/mcp-audit
Transparent proxy that intercepts, signs, rate-limits, redacts and audits MCP tool calls without modifying client or server.
hushio.github.omarei-omoto/hush
Team secrets your AI agent can use but never read: encrypted in the repo, value-blind tools.
Server and secret guardrailscom.testedtemplates/ops-guardrails
Local checks for sudo, systemd, sshd, ufw, and secret leaks before an agent applies them.
OSV Dependency Vulnerability Checkio.github.fairquery/osv-dependency-vulnerability-check
Check npm, PyPI, Go and Maven packages or lockfiles against OSV.dev: CVEs, CVSS, fixed versions.
Tenantback CAM Auditcom.tenantback/cam-audit
Audit a landlord's CAM reconciliation against the lease. Finds overcharges with clause citations.
VerifiMind PEAS - RefleXion Trinityio.github.creator35lwb-web/verifimind-genesis
X-Z-CS AI validation with auditable reasoning. 8 active tools; 5 in maintenance. v0.5.66
Sec Nportio.github.pipeworx-io/sec-nport
SEC Form N-PORT — fund and ETF holdings, asked security-first.
POPCORN Witness Verifierio.github.violetclaire/popcorn-tain-verifier
MCP server for verifying receipts: POPCORN-WITNESS/2.0 signature, digest, and time. Free, read only.
Guaritaio.github.pitroldev/guarita
Authorized security scans, evidence, fix prompts and retests for AI-built web apps.
VMware NSX Securityio.github.vmware-skills/vmware-nsx-security
VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.
Contact Verify (verify-x402)dev.workers.okwithit9.verify-x402/contact-verify
Contact Verify (verify-x402). Basic $0.002, domain $0.02, sender $0.025.
Model Finderco.indigloo/model-finder
Find the cheapest AI model that passes your tests: audit repo models, build evals, routing, sizing
Sn1per MCP Server: pentest, recon and attack surface scanningio.github.1N3/sn1per-mcp
Run scoped, authorized Sn1per pentest, recon and attack surface scans from AI agents; read findings.
Depcheckdev.kaneky/depcheck
Known vulnerabilities for exact package versions from OSV, with fixes. Paid per call, x402.
Atomadic MCPtech.atomadic/atomadic
Atomadic MCP: 68 deterministic tools for agent identity, escrow, SLA, EU AI Act compliance.
Agent Receipt Verifyio.github.holistis/agent-receipt-verify
Checks x402 endpoint conformance before an agent pays, and links the receipt to its settlement.
LEGION Verify: MCP tool-list historyio.github.Legion33shadow/legion-verify
Check if an MCP server changed its tools: signed history, per-server coverage, offline proofs.
LexiShield AI — 6-Agent GDPR, EU AI Act & Contract Redlining Servercom.run402.lexishield-ai/mcp
Run deterministic SaaS contract redlining, GDPR Art. 28 DPA & EU AI Act compliance audits.
LexiShield AI — 6-Agent GDPR, EU AI Act & Contract Redlining Serversh.surge.lexishield-ai/mcp
Run deterministic SaaS contract redlining, GDPR Art. 28 DPA & EU AI Act compliance audits.
Nahualiio.github.Arakiss/nahuali
Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.
Maillysite.mailly/mcp
A real inbox for agents: read mail, draft replies you approve, wait for verification codes.
من سجل MCP الرسمي. الإدراج ليس توصية: راجع شيفرة الخادم وصلاحياته قبل منحه الوصول إلى بياناتك. آخر مزامنة ٢٧/١٠/٢٠٢٦.
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.