"Malt" matching MCP servers:

Enables AI agents to control the DX12 Engine editor for game development, including scene editing, entity manipulation, and playback testing via natural language commands.

Policy-gated agent spend with signed receipts and rail-extract audit: a fail-closed gate issues a COSE receipt for every allowed payment, and the audit reconciles those receipts against a rail extract so a settlement with no receipt is named rather than assumed. It settles on a mock rail, holding no wallet and signing no transaction.

Enables AI coding agents in Cursor, Claude Code, Cline, and similar editors to halt repetitive failed edits after two consecutive attempts and instead gather falsifiable evidence such as git status, dirty diffs, and locked-port checks before writing more code. It also supervises wrapped shell commands, terminating hung prompts and orphaned process trees so agents can restore a clean, testable baseline.

A sample implementation of a Model Context Protocol server using Next.js and the Vercel MCP Adapter, allowing developers to create AI assistants with custom tools and resources.

Creates and manages multi-agent teams of AI coding assistants (Claude Code, Codex CLI) that collaborate in tmux terminal sessions. Enables a leader agent to assign sub-tasks to team members for coordinated development.

Bridges Cursor and Claude Desktop with the OpenClaw and Moltbook ecosystems to manage personal AI agents and communication gateways across platforms like WhatsApp and Discord. It provides MCP tools to invoke agents, manage sessions, and handle social agent interactions within a secure, virtualized environment.

Enables MCP clients to run complete browser workflows through a single run_workflow tool, with anti-detection backends, intelligent element location, automatic retries, and session persistence.

▎ Enables AI assistants to unleash a crowd of role-played virtual users — impatient shoppers, seniors, keyboard-only users, privacy hawks, chaos monkeys — on a website. Each persona browses in a real Chromium browser, files UX/QA findings in character, and the site receives a damage report with an S–F survival grade. Accusations can be cross-examined by up to three independent verification engines