دليل خوادم MCP
55,381 خادم MCP تربط مساعدي الذكاء الاصطناعي بالأدوات والبيانات، من سجل MCP الرسمي والقوائم المجتمعية، وتُحدَّث كل ساعة.
- 16 فئة
- 35,534 خادم بعيد
- يُحدَّث كل ساعة
io.github.creatorscore/creatorscore-mcpio.github.creatorscore/creatorscore-mcp
Vet creators from Claude or ChatGPT: cross-platform trust scores, risk evidence, background checks.
Teetracom.teetra/teetra
Find and call verified APIs from any AI assistant, with free trial calls and previewed writes.
Extcordio.extcord/extcord
Agent utilities: read big pages without filling context, exact math, dates, parsing. Free.
io.github.zerohourzulu/continuity-evidenceio.github.zerohourzulu/continuity-evidence
A bounded local evidence tool with current agent permission checks and durable retry handling.
io.github.inamprotocol/inam-mcpio.github.inamprotocol/inam-mcp
Check an agent's INAM reputation before trusting it, and sign a receipt when work is done.
io.github.f-tiger/agiscorecard-web3-routeio.github.f-tiger/agiscorecard-web3-route
Plan LLM fallback sequences from supplied cost, quality and latency assumptions; no live execution.
io.github.f-tiger/agiscorecard-web3-permitio.github.f-tiger/agiscorecard-web3-permit
Review declared AI data permissions, expiry and regions; model revenue splits without moving funds.
io.github.f-tiger/agiscorecard-web3-incentivesio.github.f-tiger/agiscorecard-web3-incentives
Model contributor rewards with declared quality weights and caps; separate revenue from subsidies.
China Source · 中国信源ltd.qianyuan/china-source
Structured Chinese official data for AI agents: 426 entries, JSON-LD, read-only. find/get/list
io.github.jakeyoung1/verisio.github.jakeyoung1/veris
Provenance-first web + SEC EDGAR data for AI agents: every fact carries its verifiable source.
io.github.tracelane/tracelane-mcpio.github.tracelane/tracelane-mcp
Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts
io.github.keshrath/agent-discoverio.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
io.github.pkj8282/agent-uplinkio.github.pkj8282/agent-uplink
Local messaging between AI sessions: role accounts, DMs, channels via MCP. Windows only.
io.github.P2Flux/mcpio.github.P2Flux/mcp
Let your AI assistant pay for web content in USDC (x402) within a budget you set.
io.github.Anaciber/pranaxis-mcp-gatewayio.github.Anaciber/pranaxis-mcp-gateway
Consistency verdicts for MCP tool calls: no two agents consume the same resource version twice.
io.github.forgemeshlabs/aso-score-mcpio.github.forgemeshlabs/aso-score-mcp
ASO Score MCP — the free ASO Score scanner as an MCP server. Measures your ASO Score (Agent.
io.github.forgemeshlabs/agent-readiness-mcpio.github.forgemeshlabs/agent-readiness-mcp
Agent Readiness MCP — the free Agent Readiness scanner as an MCP server. Measures your ASO Score.
io.github.forgemeshlabs/disruption-intelligence-mcpio.github.forgemeshlabs/disruption-intelligence-mcp
AI-native commercial disruption intelligence for MCP clients and x402-powered agents.
io.tokenease/gatewayio.tokenease/gateway
One MCP endpoint for 17 top Chinese LLMs. OpenAI-compatible. Up to 60% cheaper than OpenRouter.
io.github.yofor/ovanek-mcpio.github.yofor/ovanek-mcp
Ovanek MCP: Model Context Protocol server for Ovanek platform tools; writes are dry-run by default.
ai.mocopo/mocopoai.mocopo/mocopo
One remote MCP connection: 39,500+ ranked MCP servers, agent delegation, hosted tool gateway.
io.github.lnanology/xfinlabio.github.lnanology/xfinlab
Financial intelligence for AI agents: market events, sentiment, technicals, news feed.
io.github.aarshbharat/gujarati-lexicon-mcpio.github.aarshbharat/gujarati-lexicon-mcp
Grounded Gujarati dictionary for AI assistants: meanings, synonyms, idioms, inflections
io.github.douglasdemaio/vtesseraio.github.douglasdemaio/vtessera
Find vtessera agent offers, read agent cards, route an intent, and read signed attestations.
app.botnotice/mcpapp.botnotice/mcp
AI disclosure laws by business and state, each law in full, and a website AI-notice check.
io.github.epistemedeus/ein-llcio.github.epistemedeus/ein-llc
A human must claim and pay before EIN.LLC files. Agents may assess, prepare, and read status.
AssessLanecom.assesslane/assesslane
Create, review, assign and track team training assessments from your AI client.
webcheckapp.nanocorp.webcheck/webcheck
The website checker for AI agents. One call: verdict, score out of 100, fix list.
io.github.artur0x0/surfcadio.github.artur0x0/surfcad
MCP server for SurfCAD: Fully featured script CAD built on Manifold, with helpers for AI agents
io.github.bch1212/modelwatchio.github.bch1212/modelwatch
Continuous behavioral drift monitoring for LLM apps — catches silent provider model updates.
ai.stimhaus/emma-for-agentsai.stimhaus/emma-for-agents
Emma builds and edits a website for your AI agent: one create_site call, live in about a minute.
Perceptionio.github.fernikolic/perception
Narrative intelligence from thousands of curated media sources, delivered to AI through MCP.
io.github.houtini-ai/fmpio.github.houtini-ai/fmp
Access financial data and market information via Financial Modeling Prep API
io.github.houtini-ai/lmio.github.houtini-ai/lm
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
A2A Orbitcom.a2aorbit/orbit
Shared memory for AI agents: prior work, failures, checkpoints, handoffs, and artifacts.
io.github.faulkj/legionio.github.faulkj/legion
MCP-native LLM councils for debates, juries, blind panels, refinement, and custom deliberation.
io.github.Hushlor/mcp-server-tauriio.github.Hushlor/mcp-server-tauri
A Model Context Protocol server for use with Tauri v2 applications
io.github.gblinproject/gblin-treasury-risk-regimeio.github.gblinproject/gblin-treasury-risk-regime
GBLIN on Base for AI agents: risk regime, treasury plan for idle USDC, mint and redeem at NAV. Free.
com.metraipolis/knowledge-commonscom.metraipolis/knowledge-commons
Knowledge commons for AI agents: cited, licensed, queryable claims over MCP.
io.github.thealidev/dmcpsio.github.thealidev/dmcps
DMCPS: Highly secure, isolated MCP server environment giving AI agents sandboxed shell access.
io.github.qmediat/cursor-mcpio.github.qmediat/cursor-mcp
Cursor's agent (cursor-agent CLI) through MCP: any model your plan offers, resumable sessions.
io.github.Icaro0310/poordjaevinio.github.Icaro0310/poordjaevin
Typed answers with calibrated confidence for agents. Local-first, no API key.
Activepiecesio.github.activepieces/activepieces
Build and run agents and automations across hundreds of apps using natural language.
io.github.89rat/x402-checksio.github.89rat/x402-checks
Machine-payable deterministic identifier checks + signed XDR-1 receipts for agents.
io.github.justyns/silverbullet-ai-mcpio.github.justyns/silverbullet-ai-mcp
Exposes silverbullet-ai tools from a SilverBullet space to MCP clients
click.picale/picale-mcpclick.picale/picale-mcp
Pícale desde Claude, ChatGPT o cualquier cliente MCP: marca, contenido, publicaciones y resultados.
io.github.zz-plant/ambitio.github.zz-plant/ambit
Capability graph of your agent stack: what it can do, what to set up next, what breaks.
io.github.Wordpressistic/bridgisticio.github.Wordpressistic/bridgistic
Connect Claude to WordPress safely: signed requests, scoped keys, approvals, logs, snapshots.
من سجل MCP الرسمي. الإدراج ليس توصية: راجع شيفرة الخادم وصلاحياته قبل منحه الوصول إلى بياناتك. آخر مزامنة ٣١/١٠/٢٠٢٦.
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.