Servers that give an agent access to something — a filesystem, an API, a database. Every listing here was approved by a person before it appeared, and links out to the source rather than reproducing it. We deliberately don't publish ready-made config blocks: a working one carries arguments and environment variables, and those are somebody's secrets waiting to happen.
Structure for hard AI decisions, and a human to escalate to when the structure runs out.
canlicapital.com backtest validation. A verdict is not admission to anything and is not a forecast.
A webhook inbox for agents: one call returns a live URL. Mock, verify, inspect and replay.
Email for AI agents: inboxes, send/reply/forward, search, threads, webhooks — 21 SentFromAI tools.
Multi-agent orchestration via MCP. Persistent memory, inter-agent messaging, goal cascade, context budget pruning. One binary, zero config.
An MCP server that lets AI agents act like a human at a real terminal, local or over SSH.
Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.
Terminal UI engine for Go that tests can click and AI agents can drive (MCP). Zero-allocation rendering, immediate mode + Elm architecture, 3D, images, charts,…
Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions
Browser automation and computer use for AI agents. One CLI and MCP server for your signed-in browser, native macOS apps, and real iPhones.
GUI + MCP control plane for your local dev servers. Humans click, agents automate the same daemon.
Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, a…
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the mode…