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.
GeneXus MCP server with native SDK support for GeneXus 16–18 plus basic legacy compatibility for GeneXus 8, 9, 10.1–10.3, and 15 via reflection/COM drivers.
All-in-one agent harness for OpenAI Codex CLI — Boss meta-orchestrator, 17 curated agents (+17 opt-in AI specialists), 123 curated skills, 3 MCP servers. Instal…
The browser built for AI agents — fetch live pages as markdown, render JS/SPAs with built-in V8, take screenshots without Chromium, meta-search 5 engines, and d…
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
The AI-native health data engine — collect, translate, and reason with AI Agents over labs results, wearables & genomics.
Ephemora Cell is a lightweight security and execution primitive for running untrusted code inside AI agents, MCP tools, plugins, and applications.
Earlier Nobulex receipt and trust-score implementation, preserved as a prior direction. Current work: a financial decision-integrity gateway prototype at github…
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what yo…
A deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.
Contact forms that actually arrive. No SPF/DKIM, no SMTP. AI sorts them and drafts the reply.
Signed x402; starter credit: authenticated connector only; contact sales: authenticated account plan
Aircraft valuations, registry lookup, cost of ownership, market metrics, reports and logbooks.
Memory for AI agents that learns what is wrong and stops repeating it. Mark a memory wrong and it stops coming back; newer facts replace old ones. Local SQLite…
A map of your codebase for AI agents: code graph, search, call paths and change impact. No API key.
Your agent loses the plan between sessions, so saga-mcp gives it a SQLite-backed tracker for projects, epics, tasks, subtasks, dependencies, and notes: 41 MCP t…
A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models…
Web intelligence for AI agents: fetch, render, extract, research. x402 micropayments, no API keys.
Your real, logged-in Chrome as an MCP server: 60 tools, 2.75× fewer turns measured. ChromeOS too.
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.
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…