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
[WIP] Unified MCP server for DevOps engineers — query and manage Kubernetes, ArgoCD, Prometheus, and PagerDuty from any MCP-compatible AI agent.
MCP server for Docker — manage containers, images, volumes from your IDE
Reliability infrastructure for AI agents: capture every model and tool call, deterministically replay it, evaluate it against CEL contracts, and ship signed evidence bundles you can verify offline. Python + TypeScript + the rly CLI. Apache 2.0.
Model Context Protocol server for Oracle Cloud Infrastructure. Drive OCI compute, networking, storage, OKE, KMS and 50+ tools from any MCP client (Claude Code, Cursor, Codex, Continue, VS Code, Zed).
🧠 Build AI agents with advanced memory and multi-agent orchestration using this production-ready TypeScript SDK. Test before you deploy.
Prototype: Standard Terraform modules composed by InsideOut for streamlined cloud infrastructure. Based on Luther Enterprise modules.
Varity marketing site (varity.so): deploy Node and Python apps, AI agents, and LLMs in one command, 60-80% cheaper than Vercel, Render, and Railway.
End-to-end platform engineering system for self-hosted Kubernetes: OpenTofu, GitOps, OpenTelemetry, eBPF networking, MCP diagnostics, HA data services, recovery, incidents, ADRs, and RCAs.
Build and deploy an AI Studio app locally with Gemini API support for fast development and testing
Replays a stream of transactions against pluggable fraud rules and ML scorers, emitting precision/recall and alert volume from the terminal.
Make AI agents follow instructions reliably and prove what they did. State machine engine with evidence chains, multi-agent delegation, human gates, and auditable execution — via MCP or CLI.
MCP server: cross-venue spread + yield drivers, ROI radar telemetry · Hive Civilization
Private working repository for MCP registry ranking pipeline research, design, and implementation
Throwaway test service to validate the upgraded hsh-deploy script. Will be deleted within 10 min.
CLI + server for a deterministic code knowledge graph. 97 detectors across 35+ languages, Neo4j Embedded, Spring AI MCP server, REST API, and web UI. Pure static analysis — no AI, no external APIs, no telemetry.
🔍 Fetch and analyze Jenkins build logs effortlessly with the MCP server, supporting multiple instances and automatic detection from job URLs.
Production-grade Unified MCP Server architected to bridge enterprise n8n automation with agentic LLM ecosystems. Engineered for high-scale reliability with structured logging, multi-transport support (SSE/STDIO), and context-aware orchestration. Accelerating AI-native business infrastructure via secure, deterministic, and scalable workflow control.
Live infrastructure exams and regression testing for AI agents and MCP servers
Integration.app, now operating as Membrane (getmembrane.com), is an agentic integration infrastructure platform that lets AI agents, products, and internal tools connect with 100,000+ applications through a unified interface.
Manage Postgres databases, deploy sites and functions, generate images, and control agent allowances via MCP server, OpenClaw skill, and CLI tools.
Docker Helper MCP — automation tooling for docker helper. MIT.
Trust infrastructure for AI agents across organizations. Verified identity, explicit authorization, cryptographic audit trail.
Model comparison pipeline — chains delegate_to_model, create_expert, execute_expert, consensus_vote across all 5 voting strategies
Drop-in Terraform module to deploy an MCP server on AWS EKS with the FaaS-style hot-pod pattern — warm pod pool, sub-100ms invoke, HTTP + queue triggers, OTel built in. Pairs with terraform-mcp-cloudrun.