Каталог MCP-серверов
Находите серверы Model Context Protocol из официального реестра. Прозрачные сведения от разработчиков, а не сертификат безопасности.
Подборки по направлениям
Найдите подходящее направление
Тематические подсказки по описаниям разработчиков, а не проверенные возможности серверов.
Избранное остаётся в браузере. Сохраните сервер, чтобы увидеть подсказки.
Нажмите / для быстрого поиска
Найденные серверы
17 827 записей · Публикация в Registry ≠ техническая проверка NexIP
io.github.HMAKT99/scbee-mcp
io.github.HMAKT99/scbee-mcp
Score repos for launch and agent readiness, find verified agents, read collaborations. Read-only.
io.github.HMAKT99/erabi
io.github.HMAKT99/erabi
Check paid x402 APIs before your agent spends: signed uptime/price attestations. Zero-config join.
ClawTank
io.github.HMAKT99/clawtank
Let agents see and drive a Mac: screenshots, clicks, typing, apps and virtual displays.
io.github.HMAKT99/akf
io.github.HMAKT99/akf
Trust metadata for AI agents — check files before building on them, stamp verified work.
io.github.HBarefoot/engram
io.github.HBarefoot/engram
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
io.github.H129hj/checkmcp
io.github.H129hj/checkmcp
Audit any MCP server's security & quality — OWASP MCP Top 10 + explainable 0-100 MCP Score
agent-in-browser
io.github.Gwakko/agent-in-browser
Real browser for any agent: Chrome/Edge/Brave via CDP, Firefox via BiDi. Refs, forms, console, net.
FerryCat
io.github.GuoBug/ferrycat
Contract-driven cross-host agent handoff, code review & verification harness via MCP & SQLite WAL
io.github.Gunsmith-Academy/woody-mcp
io.github.Gunsmith-Academy/woody-mcp
Woody, the AI firearms expert. Verified specs, legal lookups, and knowledge base.
GetABrain
io.github.Guitarmaniac24/getabrain
Real human judgment as agent tools — ask a question, get a structured human answer back.
QECTOR Quantum Error Correction
io.github.GuillaumeLessard/qector-desktop
Local quantum error correction tools; decoder output verified against H c = s (mod 2).
Lex
io.github.Guffawaffle/lex
Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.
PrufGate
io.github.GuardianVigil-Labs/prufgate
Read-only tools that check whether code, and the tests that claim it works, are real.
io.github.GuardBee/vulnerability-scanner
io.github.GuardBee/vulnerability-scanner
Triggers GuardBee scans, queries findings, AI-assisted remediation guidance
io.github.GuardBee/vector-store-scanner
io.github.GuardBee/vector-store-scanner
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
io.github.GuardBee/unbounded-consumption-auditor
io.github.GuardBee/unbounded-consumption-auditor
Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)
io.github.GuardBee/toxic-flow-auditor
io.github.GuardBee/toxic-flow-auditor
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
io.github.GuardBee/tool-poisoning-scanner
io.github.GuardBee/tool-poisoning-scanner
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
io.github.GuardBee/threat-rules
io.github.GuardBee/threat-rules
GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection