Серверы, которые подключаются к Claude по ссылке или через конфиг. На карточке каждого коннектора — адрес сервера и пошаговая инструкция для Claude.
Statistical checks an agent runs before trusting an AI eval number (is 1 real, judge bias, more).
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
WHOIS domain MCP server that query the WHOIS information using IP2WHOIS API.
IP Geolocation MCP server that query the geolocation information using IP2Location.io API.
Parallel Sort MCP - High-Performance Log File Processing for LLMs with advanced sorting and analysis
Inspect and manage IONOS CLOUD infrastructure via MCP.
Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
Disposable Algorand wallet for AI agents.
Linters check your code.
Extract, create, convert & validate invoices (UBL, CII, XRechnung, ZUGFeRD, PDF, Excel)
MCP server enabling AI assistants to build, test, and debug Zotero plugins
AI-powered i18n platform with 50+ tools for translations, OTA releases, and more.
Parse, validate, query, and render IntentText (.it) documents for AI agents
Turn an IDF domain into an MCP server with invariants and role scopes in every tool description.
Run the Intelliverse platform from any agent: apps, API keys, knowledge bases, email, media, chat.
Free, local SEO + GEO audits for AI assistants - no signup, nothing leaves your machine.
MCP server for Instagit — AI-powered Git repository analysis for coding agents
Drive your own logged-in Instagram session via the INSSIST extension: read, publish, DMs, analytics.
MCP server for DefectDojo: 24 tools with RBAC, HMAC audit chain, and SIEM forwarding
Read-only MCP server for the Symbol blockchain (XYM): node health, harvesting, voting keys.
Security co-pilot for AI agents.
Open-source bitemporal memory layer for LLM agents — knowledge graph with conflict resolution.
Curated sshprobe diagnostics and single-host sshexec over an allowlisted SSH fleet.
Runs a command in a throwaway Kubernetes pod and returns exit code, output and artifacts.
Single exec tool running caller Python in a network-isolated locked-down sandbox.
Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.
Govern your backend control plane from your AI agent - signed, human-approval-gated.
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
legal-ge: поиск проверенных юристов Грузии по запросу на естественном языке
Japanese document AI for agents — invoice/meishi extraction, OCR, classification (hosted API).
Расскажите, какой сервис вам нужен, или добавьте свой MCP-сервер: проверим и опубликуем в каталоге.
Предложить коннектор