AI & Agents MCP Servers

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.

Port Authority Agent Terminal Source verified npm
A
port-authority-agent-terminal-mcp

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

AI & Agents Score 93/100 14 findings 89/wk Cap. High
Youtube Music npm
A
@instructa/mcp-youtube-music

Simple MCP Starter Package

AI & Agents Score 93/100 1 finding 84/wk Cap. High
Orchex npm
A
@wundam/orchex

Autopilot AI orchestration — auto-plan, parallelize, and execute with ownership enforcement

AI & Agents Score 93/100 3 findings 82/wk Cap. High
Gateway Scan npm
A
mcp-gateway-scan

Read-only static scanner for MCP/agent-gateway production-readiness anti-patterns. Scores a repo across 7 dimensions.

AI & Agents Score 93/100 2 findings 80/wk Cap. High
Subscriber npm
A
@helloaigent-dev/subscriber

Hello Aigent reference subscriber — an MCP server that lets any agent subscribe to any Hello Aigent feed, fetch signed updates, verify them, and act.

AI & Agents Score 93/100 1 finding 80/wk Cap. High
Steam Local npm
A
steam-local-mcp

A Windows Steam MCP server with local client controls and optional Steam Web API insights.

AI & Agents Score 93/100 1 finding 77/wk Cap. High
Email Guard npm
A
email-guard-mcp

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.

AI & Agents Score 93/100 6 findings 74/wk Cap. High
Glassbox Framework npm
A
@glassbox-framework/mcp

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.

AI & Agents Score 93/100 1 finding 74/wk Cap. High
Roku npm
A
roku-mcp

MCP server for Roku device automation — deploy, ECP control, screenshots, debug console, and BrightScript profiler analysis

AI & Agents Score 93/100 6 findings 73/wk Cap. High
Agent Firewall npm
A
agent-firewall-mcp

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.

AI & Agents Score 93/100 6 findings 72/wk Cap. High
Recipe npm
A
@cookwith/recipe-mcp

MCP server for AI-powered recipe generation and transformation

AI & Agents Score 93/100 1 finding 69/wk Cap. High
Aegis npm
A
aegis-mcp-server

MCP enforcement layer for the Aegis agent governance specification

AI & Agents Score 93/100 15 findings 68/wk Cap. High
Imgx npm
A
imgx-mcp

AI image generation and editing MCP server with context-aware prompt optimization, 24 editing techniques, and session undo/redo

AI & Agents Score 93/100 3 findings 68/wk Cap. High
Genable npm
A
genable-mcp

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

AI & Agents Score 93/100 1 finding 66/wk Cap. High
Code Guard npm
A
@mlawsonking/code-guard-mcp

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.

AI & Agents Score 93/100 6 findings 65/wk Cap. High
Docx Forge npm
A
docx-forge-mcp

MCP server for creating, reading, and manipulating Word documents (.docx) — the production-grade document automation tool for AI agents

AI & Agents Score 93/100 1 finding 63/wk Cap. High
Pixel Surgeon npm
A
pixel-surgeon-mcp

MCP server for AI image & video generation, editing, and region repair. Powered by Gemini and OpenAI.

AI & Agents Score 93/100 2 findings 62/wk Cap. High
Payment Guard npm
A
payment-guard-mcp

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.

AI & Agents Score 93/100 6 findings 60/wk Cap. High
Package Guard npm
A
package-guard-mcp

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.

AI & Agents Score 93/100 6 findings 58/wk Cap. High
Baton npm
A
baton-mcp

BATON — hand off AI work with a signed verification receipt (independent E2E-proven), over MCP

AI & Agents Score 93/100 2 findings 55/wk Cap. High
Supernote npm
A
supernote-mcp

Unofficial MCP server for the Ratta Supernote e-ink tablet: capture the screen, read/render saved notes, and upload files over the LAN.

AI & Agents Score 93/100 1 finding 55/wk Cap. High
My Minimax npm
A
my-minimax-mcp

MCP server wrapping MiniMax AI as autonomous code executor with agent loop for Claude Code

AI & Agents Score 93/100 1 finding 53/wk Cap. High
Forage npm
A
forage-mcp

Self-improving tool discovery for AI agents. Agents find, install, and learn to use new tools automatically.

AI & Agents Score 93/100 3 findings 52/wk Cap. High
Mnehmos.rpg.mcp npm
A
mnehmos.rpg.mcp

Complete tabletop RPG game engine via MCP - D&D 5e combat, procedural worldgen, NPC memory, 28 consolidated tools

AI & Agents Score 93/100 2 findings 52/wk Cap. High