دليل خوادم MCP
53,397 خادم MCP تربط مساعدي الذكاء الاصطناعي بالأدوات والبيانات، من سجل MCP الرسمي والقوائم المجتمعية، وتُحدَّث كل ساعة.
- 16 فئة
- 33,774 خادم بعيد
- يُحدَّث كل ساعة
Omnisealio.github.PureCipher/omniseal
Conceal, retrieve, verify, and remove hidden files with PureCipher Omniseal.
Electron MCP Serverio.github.YawLabs/electron-mcp
Electron.js MCP server — IPC scaffolding, security auditing, build tooling for AI assistants
npm Registry MCP Serverio.github.YawLabs/npmjs-mcp
npm registry MCP server — package intelligence, security audits, dependency analysis
citepathai.citepath/citepath
Citepath public MCP server for LLM readiness audits and public scan results.
Averraycom.averray/mcp
Paid agent work and paid verification, settled in USDC. Verified outcomes get signed receipts.
HumanMirror Outcomefr.humanmirror/outcome
Verified AI-agent outcomes: secret scanning, JSON cleanup, dedupe, anomaly and schema checks.
JSON to TOONio.github.karta9821/json2toon
Convert JSON to TOON (about 43% fewer LLM tokens) and TOON back to JSON. Free, no auth.
Skuuy MCPio.github.deaabie/skuuy-mcp
13 privacy-first network, auth & web tools for AI agents — no API key, 60 req/min free.
HeaderGuarddev.workers.mike-tusa.headerguard/headerguard
Scan a website's HTTP security headers (HSTS, CSP, framing, COOP/CORP, cookies). Score + fixes.
LLMVerifyio.github.subodhkc/llmverify
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
Pubmedio.github.pipeworx-io/pubmed
PubMed MCP — wraps the NCBI E-utilities API (biomedical literature, free, no auth)
Latchpointio.github.robyroro/mcp-latchpoint
Offline, read-only auditing of MCP client configuration files with redacted findings
AION Agent Assurance Gatewayio.github.danieljames-dev/agent-assurance
Read-only MCP gateway. Paid verify is $0.01 USDC on Base.
Agent-Shieldio.github.startekenterprises-ai/agent-shield
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Private SuperIntelligencesi.privatesuperintelligence/private-superintelligence
Private SuperIntelligence by Mitosis Labs: define the term, see privacy layers, join the waitlist.
Tanod Securitydev.tanod/security
Contract and agent-package scans, phishing URL and OFAC checks, domain and header checks.
Keyspoorio.github.majiayu000/keyspoor
Offline secret scanning for AI agents. Redacted findings; scans text and files in a chosen root.
Cybret findingsai.cybret/findings
Validated API and app vulnerability findings with remediation guidance.
WHP Standingio.github.wheelerhubbell/whp-standing
WHP Standing x402 on Base: evaluate, patch, ept/core 1 USDC; audit 2; priority 5; ping 0.10
Keystashio.github.thu-lawyer/keystash
Keychain-backed secret broker: an AI agent can use your keys, but no tool ever returns one.
Ntfy Me MCPgithub.com/gitmotion/ntfy-me-mcp
Send and fetch ntfy notifications on a self-hosted ntfy server, with token auth support.
agentguardio.github.agentwares/agentguard
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
Owidio.github.pipeworx-io/owid
OWID MCP — Our World in Data chart/indicator access (free, no auth)
Gadriel AI Security Harnessio.github.Gadriel-ai/gadriel
AI Security Harness: SAST, secrets, deps, containers, config & OWASP LLM. Scans locally.
OpenWrt MCPio.github.stanislav-testhub/openwrt-mcp
MCP server that runs on an OpenWrt router: deny-by-default policy, audit log, rollback-armed changes
Secrets-LEio.github.nolindnaidoo/secrets-le
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
i18n-LEio.github.nolindnaidoo/i18n-le
Audit translation catalogues: missing keys, broken placeholders. Never returns a translation.
DDG Agent Servicescom.daedalusdevelopmentgroup/ddg-agent-services-mcp
Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.
FEDLIN Scannerscom.fedlin/fedlin-mcp-server
Exposes FEDLIN's public security scanners as agent-callable tools over Streamable HTTP.
Kairos Signal — verifiable DePIN data APIcom.kairossignal/kairos-signal
DePIN network telemetry with the source, as_of time and an upstream verify URL on every value.
VERIDEXes.veridexia/veridex-mcp
Verify Spanish companies by CIF: registry data, status and BORME filings, paid per call over x402.
AuditSocials Complianceio.github.eminegurcu/auditsocials-compliance-mcp
Pre-publish policy check for AI-generated social & ad content across 8 platforms.
DepScoutio.github.yc-droid/depscout
Scan packages and lockfiles (npm, PyPI, Go, Maven, Cargo, NuGet) for vulnerabilities and malware.
ResponseHubai.responsehub/responsehub
Answer security questionnaires and RFPs from your AI knowledge base.
pdata Prediction Marketsworld.pdata/mcp
Polymarket, Kalshi + 6 more prediction markets: live odds, volume, movers. Read-only, no auth.
Deepsleuthio.github.DeepSleuth/deepsleuth
Deterministic, no-LLM security scanner for MCP servers, plus an inline proxy gate.
Agent Blast Radiusio.github.makash/agent-blast-radius
Scan what an AI agent running as you can reach; optionally verify which keys are live (x402).
Authboxgithub.com/MARUCIE/authbox
Zero-knowledge password manager and MCP credential gateway: policy-gated agent access, deterministic passwords, BIP-39 recovery and a hash-chain audit trail.
AgentWatchdev.workers.agentwatch.agentwatch/agentwatch
Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
Verified by NPCio.github.bayo-de/npc-verify
Check products, credentials, claims, and agents against NPC Labs verification records.
quant-swarmio.github.blink1217/quant-swarm
Risk-first pre-trade checks, PIT data, leakage audits, and a Shadow Tournament vs a live champion.
Kodemcom.kodemsecurity/kodem
Ask about your Kodem Security data and act on findings in plain language, with your permissions.
TOVREK Current-State Resolvercom.tovrek/current-state-resolver
Verify DOI metadata before autonomous action; preserve conflicts, provenance, and UNKNOWN.
VerifyAXio.github.verifyax/mcp-server
Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.
Auditraio.github.mwstech/auditra
Read-only MCP server for WordPress plugin audits: vulnerabilities, bloat, cron, orphaned tables.
Apple Mail MCPio.github.jakobfigur/apple-mail-mcp
Privacy-first local MCP for Apple Mail on macOS: inbox context, drafts, approvals, and follow-ups.
NAIF Gravity Diagnostic — Free MCP/API/Webhook Triagecom.naifgravity/diagnostic
Free MCP, API auth, webhook and schema diagnostics with bounded checks and safe quote routing.
HumanFncom.humanfn/humanfn
Qualified human outcomes for AI agents: attorney review of SaaS Terms/Privacy, on-site checks.
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.