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
MCP server that gives AI coding assistants production-grade engineering standards — SOLID, testing, architecture, CI/CD — for Claude, Cursor, Copilot, Windsurf, Cline & Aider
Build AI applications with this curated collection of free LLM APIs, coding copilots, and infrastructure tools.
Context engineering toolkit for AI agents. 24 MCP tools across retrieval, memory, context, and team telemetry. .NET 10. No cloud deps.
Deploy any MCP server on AWS, GCP, or Azure — serverless, zero idle cost, full CI/CD, no long-lived credentials.
The open-source AI agent orchestration platform. Visual workflow engine, 25+ pre-built agents, multi-provider LLM support (OpenAI, Anthropic, Gemini, DeepSeek, Ollama). Self-hosted. One-command Docker deploy.
Thermodynamically honest AI infrastructure — MCP gateway + physics kernel (Rust)
Polyglot observability MCP server — unified observability across multiple languages and runtimes
A Model Context Protocol (MCP) server that enables AI assistants to efficiently filter and analyze Cloud Platform logs by specific prefixes and patterns.
Urule — The open-source coordination layer for AI agents. Deploy, orchestrate, and govern.
MCP server for Grafana, Prometheus, Kafka UI, and Datadog — bring your own credentials (BYOK)
Kubernetes workload analyzer that generates actionable HPA/VPA/resource scaling recommendations using Prometheus metrics and kubectl data
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
MD-driven agent CLI for code, infrastructure, and automation. 6 providers, 8 tools, zero SDK dependencies.
Self-hosted web crawling and RAG pipeline with MCP tooling for scrape, crawl, ingest, embed, query, and ask workflows.
GitOps Helm charts for a self-hosted AI platform — LibreChat, model serving, MCP servers, Keycloak, and supporting infrastructure, deployed via ArgoCD.
🔒 Manage and monitor reusable autonomous agents securely with the MCP Supervisor, designed for seamless operation on Ubuntu 24.04.
MCP server for Swiss federal law (Fedlex) — search the SR, monitor legal changes, and query BBl/treaties via Claude Desktop or Claude.ai
APIs.io federated API search network — homepage, blog, and build pipeline. https://apis.io
The first AI-First IDE for QA. Test, design, and validate APIs with AI assistance from your desktop, CI/CD, or your favorite AI assistant.
Pluralistic human evaluation infrastructure for AI in production
Azure-first IncidentOps backend for ingesting engineering evidence, indexing it with PostgreSQL/pgvector, and powering cited search, investigation, workflows, and MCP.
MCP server for Jungle Grid lets agents submit, monitor, and retrieve logs from AI workloads.
Cryptographic-proof data infrastructure for multi-party & AI-driven workflows: verifiable credentials (SD-JWT VC, OpenID4VCI/VP, HAIP), Merkle-chained distributed registers, HD wallets, post-quantum crypto (ML-DSA/ML-KEM), selective disclosure, and a 36-tool MCP server. .NET 10 / Aspire.
Seq Open Telemetry MCP Server