SkillAvatars
Model Context Protocol servers - tools, resources, and prompts for Claude and other AI assistants.
Start Better
MCP discovery works better when people begin from a job to be done. Route them into a scene, a curated stack, or a high-signal tag before they start scanning tool cards.
Scenes
Stacks
Popular tags
Showing 24 of 806 MCP tools
Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.
Agent-native ZK proof infrastructure with AWS Nitro Enclave TEE + ERC-8004 identity. Powers OpenStoa (1st Place at The Synthesis Hackathon — Agents That Keep Secrets).
Enterprise-grade defense framework for AI agents. Five-layer pipeline (sanitizer + injection detector + RBAC + audit + human gate). MCP-native. HIPAA / SOC 2 / NERC CIP ready. Apache 2.0.
An enterprise-grade AI Operations Hub built on Amazon Bedrock AgentCore. Features a distributed 11-node Serverless MCP mesh, Agent-to-Agent (A2A) escalation, and stateful self-healing for e-commerce diagnostics.
📇 Access Google Contacts securely with a serverless MCP server on AWS Lambda, using per-user OAuth for real-time, privacy-focused data retrieval.
Local intelligence infrastructure -- routing, memory, provenance. Local-first.
Connect AI agents to EasyPanel to deploy and manage infrastructure using natural language commands via the MCP protocol.
Local AI agent for US weather alert monitoring using MCP, PostgreSQL and NWS API
MCP server: static security audit of Kubernetes manifests via kube-linter. 63 checks across 7 categories. Pay-per-event via Apify Actor Store.
Deploy static sites and manage private cloud storage directly through your AI agent using TARS.
A beginner-friendly MCP (Model Context Protocol) demo — connects Azure OpenAI to local tools (calculator + weather) via a client/server setup using stdio transport.
Deploy-your-own SimpleFIN finance MCP server on Cloudflare Workers
🏴☠️ Trust Infrastructure for AI Agents — Security, scoring, and observability for the MCP ecosystem
MCP server that turns Claude into an Ashby ATS copilot — re-engagement campaigns, deep pipeline reports, historical narratives, and personalized outreach.
Structured failure knowledge infrastructure for AI agents — dead ends, workarounds, and error transition graphs.
Indox is open-source search infrastructure for AI agents. Self-hostable, multi-source.
Query the ISTAT (Italian National Institute of Statistics) SDMX 2.1 catalogue via a Python MCP server, driven by a Microsoft Agent Framework agent (Ollama / Azure OpenAI). Includes a Docker Compose stack, Bicep IaC for Azure Container Apps, GitHub Actions CI, GHCR image publishing, and OIDC-based cloud deploy.
Agentic runtime for KAOS: Runner, SessionMemory (with reflexion lessons), 5 patterns (Chat/PlanExecute/Research/Findings/Router), 14 MCP tools, FastAPI REST API, audit-trail telemetry recorder.
Source-available public-preview surface for YIYUAN-ASSETS, a graph-first governed developer infrastructure substrate.
MCP server exposing Grafana and its Mimir/Loki/Tempo/Alertmanager datasources, with OIDC-based per-org RBAC.
Decentralized AI Memory Network (DAMN) — a persistent learning and memory-sharing infrastructure for autonomous agents. Blockchain + IPFS-based memory layer enabling cross-agent experience reuse and scalable distributed intelligence.
🤖 Optimize LLM usage by streamlining tool calls with code generation and sandbox execution for reduced costs and latency in any model.
🔍 Build local AI infrastructure on M2 MacBook Air with zero cloud dependencies, ensuring unlimited usage and complete privacy.
Production-grade MCP (Model Context Protocol) server in Quarkus - safely expose your observability stack to AI assistants.