Journal, approve or block, and sandbox every MCP tool call your AI agent makes
Runs locally- Open source
- Security
Journal, approve or block, and sandbox every MCP tool call your AI agent makes
Runs locallyLocal MCP server giving editors image, video, RAG and code-map tools from Guaardvark
Runs locallyGive two agents on two machines one encrypted shared folder, peer to peer
Runs locallyHand hard, contested questions to a research engine that labels each claim's support
Runs locallyLocal MCP server for reading and updating cattle and sheep records in a Ranch.Bot account
Runs locallyHyperliquid perps trading for AI agents, with the account key kept on an offline phone
Runs locallySecurity scanner that runs inside your AI editor for code written by AI builders
Not checked yet
Manage Ghost Networks private mesh networks, hubs, VPN and devices from your AI client
Runs locallyQuery your team's AI coding-agent session history and apply fix recommendations
Not checked yetCheck, edit and preview RDLC reports, and turn Markdown into Word, PowerPoint or PDF
Not checked yetLets your coding agent read and resolve the review comments you leave in the Reado IDE
Runs locallyLocal operator tools over your sessions, files, shell and devices, driven by an AI agent
Runs locallyLong-term memory for Claude as Markdown in a git repo you own, built to survive compaction
Runs locally
Install, launch and remote-control Minecraft Java clients and servers, headless or not
Runs locallyLocal-first data-quality scans with evidence and previewable, reversible repairs
Runs locallyAdd, organize and check off tasks in an ADHD-friendly to-do app, from an AI assistant
Not checked yetLets a coding agent launch Claude Code and Codex sessions that the user can watch
Runs locally
Evidence from strace, py-spy, perf, lsof and tcpdump for agents debugging live processes
Runs locallyOffline pixel-art editor for agents and shells: sprites, animation, GIFs and fonts
Runs locallyRead-only access to your notes, tasks, people and meetings from Claude, Codex or Cursor
Not checked yetLet Claude Code, Codex, Grok and Antigravity review each other's work
Runs locallyRead-only MCP endpoint on a self-hosted or cloud web analytics instance
Not checked yetRead-only MCP server that finds deleted SQL Server rows in the transaction log
Runs locallyContact-centre workforce management on your own server, open to scripts and agents
Not checked yetTyped, policy-checked server operations for AI agents, with approvals and an audit log
Runs locallyPrivate on-device speech to text for AI assistants: transcribe files, search dictations
Runs locallyRun backtests from a coding agent through the Stochastly desktop app
Runs locallyPlaywright MCP-compatible browser automation running on CloakBrowser Chromium
Not checked yetLocal checks for sudo, systemd, sshd, ufw and secret leaks before an agent runs commands
Not checked yetOpen-source reader that lets agents inspect raw lab-instrument files offline
Runs locally