MCP servers for building, orchestrating and running autonomous AI agents, multi-agent systems and LLM tooling. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.
Cross-platform (Windows + macOS) lane coordinator for AI coding agents (Claude, Codex, etc.) — keeps multiple local agents from colliding on dev-server ports, Chrome debug ports, and Chrome user profiles. Includes a CLI, an MCP server, and a native Tauri
Simple MCP Starter Package
Autopilot AI orchestration — auto-plan, parallelize, and execute with ownership enforcement
Read-only static scanner for MCP/agent-gateway production-readiness anti-patterns. Scores a repo across 7 dimensions.
Hello Aigent reference subscriber — an MCP server that lets any agent subscribe to any Hello Aigent feed, fetch signed updates, verify them, and act.
A Windows Steam MCP server with local client controls and optional Steam Web API insights.
MCP server: email safety for AI agents: scan inbound email for 'AI agent phishing' (prompt-injection/spoof) before acting, and outbound email for secret/PII leaks + deliverability before sending. Deterministic, free, no LLM.
Glass Box Framework MCP server — runtime constitutional verification for AI answers, with claim-level reasoning chains, formal ECS scoring, 7-angle red team (Glassbox Court), and deterministic audit logs.
MCP server for Roku device automation — deploy, ECP control, screenshots, debug console, and BrightScript profiler analysis
MCP server: input/output safety gate for AI agents: detect prompt injection/jailbreak, vet URLs & IPs, check pwned passwords (HIBP k-anonymity), scan for leaked secrets & PII. Deterministic, free, no LLM.
MCP server for AI-powered recipe generation and transformation
MCP enforcement layer for the Aegis agent governance specification
AI image generation and editing MCP server with context-aware prompt optimization, 24 editing techniques, and session undo/redo
Write-side MCP server for Figma — build, edit, restructure, and search Figma designs from Claude Code, Cursor, Cline, or any MCP client. Your agent is the LLM, so no Figma-plugin API key is needed. Complements Figma's official MCP (which is read-only). 39
MCP server: security scanner for AI-generated code: the agent scans its own code/diff before committing. Detects injection, SSRF, hardcoded secrets, weak crypto, unsafe deserialization, TLS-off, XSS. Deterministic, free, no LLM.
MCP server for creating, reading, and manipulating Word documents (.docx) — the production-grade document automation tool for AI agents
MCP server for AI image & video generation, editing, and region repair. Powered by Gemini and OpenAI.
MCP server: pre-send risk check for AI agents that move money: screen a crypto address (or ENS name) and payment URLs for OFAC sanctions, scam/abuse blocklists, and on-chain risk before a transfer. Deterministic, no LLM.
MCP server: the pre-install supply-chain guard for AI coding agents: verify a package exists (catch slopsquat/hallucinations), check vulnerabilities & malware (OSV), detect typosquats, audit a whole dependency list. Deterministic, free, no LLM.
BATON — hand off AI work with a signed verification receipt (independent E2E-proven), over MCP
Unofficial MCP server for the Ratta Supernote e-ink tablet: capture the screen, read/render saved notes, and upload files over the LAN.
MCP server wrapping MiniMax AI as autonomous code executor with agent loop for Claude Code
Self-improving tool discovery for AI agents. Agents find, install, and learn to use new tools automatically.
Complete tabletop RPG game engine via MCP - D&D 5e combat, procedural worldgen, NPC memory, 28 consolidated tools