Серверы, которые подключаются к Claude по ссылке или через конфиг. На карточке каждого коннектора — адрес сервера и пошаговая инструкция для Claude.
MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history
36 tools for AWS infrastructure, security compliance, AI workflows, and ACI governance.
MCP server for Ryvo Protocol state reads and prepare-only payment-channel actions.
MCP server for Ryvo Gateway x402, Helius Wallet, and Tokens API market data.
Read and write WiseGrid sheets, rows, columns and reports from any AI agent.
Grant management for AI agents: deadlines, business-day math, budgets, in-kind value.
Twitter/X tools for AI agents — read timelines, post tweets, search, and engage
League of Legends math for AI agents: MMR estimation, climb projections, KDA, hours.
33 image tools: free local editing, AI upscaling, background removal, and product photos
Technical SEO tools for AI agents: structured data, meta tags, robots, SERP truncation.
Claude Desktop reminders for Windows.
Agent-harness picks and decision guides; pickinfrastructure adds live GitHub/HN discovery.
Access the full Runware API as MCP tools: image, video, audio, 3D, and text.
Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.
Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.
Security guardrails for AI agent payments
Centralized API gateway routing to MCP servers with per-call billing
Real-time agentic newsfeed for MCP tools and capabilities
Agent wallet and budget management for AI agents
Immutable audit trail for agent-to-agent interactions
Indexes your project's markdown docs and serves them to any agent via local hybrid search.
Inspect and query MySQL 5.0–5.6; opt-in INSERT/UPDATE/DELETE/DDL.
Wraps the WorkspaceGuard CLI as a single generic MCP tool for workspace usage checks.
Classifies GPU workloads as inference or training from telemetry alone via MCP tools.
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
Wraps the truesignal CLI as a single generic MCP tool for threat/connector status checks.
Wraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.
Compares AI coding tool spend before and after a migration via MCP tools.
Расскажите, какой сервис вам нужен, или добавьте свой MCP-сервер: проверим и опубликуем в каталоге.
Предложить коннектор