Infrastructure

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/s

MCP server exposing policy-gated, audited SSH access for Linux and Windows hosts via the Model Context Protocol.

Host-side Model Context Protocol client for TanStack AI: discover and run MCP server tools, resources, and prompts in any adapter's chat() loop, with generated end-to-end types.

MCP server exposing live browser telemetry (console logs, network requests, screenshots, Lighthouse audits) from your real Chrome session

MCP server for Coolify — 44 optimized tools for infrastructure management, diagnostics, and documentation search

Coherence infrastructure for self-evolving AI agents — on the Claude Code or Codex subscription you already have.

Unified AI router with 160+ providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.

Generate AI summaries of test results using a wide range of AI models like OpenAI, Anthropic, Gemini, Mistral, Grok, DeepSeek, Azure, Perplexity, OpenRouter, and custom OpenAI-compatible APIs

Domain-aware MCP server selection and access boundaries for Pi sessions composed with DoomPi.

AWS MCP server — call any AWS API from AI assistants, with first-class SSO re-login (no more 'browser won't open' dead ends)

Node.js/TypeScript MCP server for AWS Single Sign-On (SSO). Enables AI systems (LLMs) with tools to initiate SSO login (device auth flow), list accounts/roles, and securely execute AWS CLI commands us

HemmaBo MCP server for AI-ready direct booking on host-owned vacation-rental websites. AI agents discover host booking pages and verify signed stay offers (VRP · Ed25519/JWKS). HemmaBo is the host-own

Config-driven MCP wrapper for atrib's verifiable action layer. Gates, signs, logs, and mirrors tool calls from any upstream MCP server.

A Model Context Protocol (MCP) server for Kubernetes with 270+ tools, 8 resources, and 8 prompts for AI assistants

MCP server for GitHub Actions — view workflow runs, read logs, re-run failed jobs, and manage CI/CD from your IDE

Omni-FS-MCP is an MCP server that supports managing multiple types of file systems, such as local FS, S3, R2, B2, WebDAV, and others, in one MCP server. It is built on top of OpenDAL.

MCP Platform: Production-ready Model Context Protocol server deployment and management platform

MCP server for Microsoft 365 and Intune management with 33 tools for Entra ID, devices, Autopilot, and more

A Model Context Protocol (MCP) server for Kubernetes with 270+ tools, 8 resources, and 8 prompts

An open source MCP server empowering SREs with intelligent observability, predictive analytics, and AI-driven automation across Kubernetes, OpenShift, and Tekton environments.

MCP server that gives AI assistants 53 tools to manage Portainer: deploy and update stacks, inspect and roll out Swarm services/tasks/nodes, manage containers, volumes, networks, exec commands, pull i

[DEPRECATED] Model Context Protocol (MCP) server for Dynatrace. Migrate to dynatrace-for-ai + dtctl or the Dynatrace Remote MCP Server.

Auth0 Model Context Protocol (MCP) Server (Beta) — A secure and extendable implementation of an MCP server that provides AI assistants with controlled access to the Auth0 Management API through natura

Audit AI applications and agents for security risks before commit, PR, merge, or deployment. Deterministic findings with coverage and evidence receipts.

Deploy static websites, landing pages, and prototypes instantly from AI agents. Start with the hosted endpoint at mcp.shipstatic.com (no install, no signup, no API key), or install this package to dep

Upsilon measurement engine distributed through the sigrank CLI/MCP compatibility package, with SigRank public leaderboard tools.

CLI and MCP bridge for NicheDB: browse collections, manage sources and feeds, search items, from any deployment

MCP server for the 1claw secrets vault — lets AI agents fetch, store, and manage secrets at runtime

MCP for LUNO, the AI-era Backend Platform — not the Luno crypto exchange. Agents BUILD/OPERATE (Claude Code, Cursor, Codex). Humans REGISTER/GOVERN. Applications CONSUME. luno.rest · doc.luno.rest · n

A-Team MCP Server — build, validate, and deploy multi-agent solutions from any AI environment

Cedar policy enforcement and signed receipts for AI agent tool calls, guided repository review, bounded coding work and exact human approvals. Built by ScopeBlind.

Model Context Protocol server for Impreza Host — privacy-first, no-KYC hosting an AI agent can run end-to-end: self-onboard its own anonymous account (no e-mail), fund it in Bitcoin/Monero, then deplo

ExecBro: React Native AI debugger and devtools MCP server. Gives AI agents eyes and hands in your running app (logs, network, state inspection, tap, screenshot).

What changed on your server, and only what's worth telling — CLI, dashboard and MCP server in one binary

Rank log patterns by cost, then compact, tier down or offload them. No log data reaches log10x.

MCP security scanner and CI gate. Test, secure, and monitor MCP servers with attack simulation, schema drift detection, health scoring, and SARIF before agents depend on them.

Tailscale MCP server: admin-API tools for devices, ACLs, DNS, auth keys, users, and audit logs, plus a CLI to validate and deploy ACLs.

Caddy MCP server for Claude Code, Cursor, and any MCP client: admin API, config, routes, reverse proxy, TLS, PKI, metrics

Azure MCP Server - Model Context Protocol implementation for Azure

Azure MCP Server - Model Context Protocol implementation for Azure, for win32 on x64

Azure MCP Server - Model Context Protocol implementation for Azure, for linux on x64

Azure MCP Server - Model Context Protocol implementation for Azure, for darwin on arm64

MCP Server for GCP environment for interacting with various Observability APIs.

MCP server for interacting with Kubernetes clusters via kubectl

Model Context Protocol (MCP) server for Kubernetes and OpenShift

Workflow runtime for AI agents - deterministic pipelines with approval gates

Framework for testing AI coding agents in isolated sandboxes

Detect AI agents. Serve them markdown. Audit your site against the Agent Readability Spec.