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.

Zynd npm
B
zynd-mcp-server

MCP server that turns Claude into a Zynd network agent: auto-bootstraps developer + persona, runs a parallel inbox for incoming A2A traffic, lets Claude call other agents over sync/push channels, and recognizes push-callback replies from tasks Claude init

AI & Agents Score 83/100 6 findings 16/wk Cap. Critical
Agent Portal npm
B
mcp-agent-portal

Unified Agent & MCP Control Plane — aggregator for AI agents and MCP tools

AI & Agents Score 83/100 16 findings 15/wk Cap. High
Homaruscc npm
B
homaruscc

MCP server that gives Claude Code a body — messaging, memory, identity, timers, browser automation, and dreams

AI & Agents Score 83/100 16 findings 14/wk Cap. High
Agent Device npm
B
agent-device

Agent-native CLI for AI app automation across iOS, Android, tvOS, Android TV, macOS, Linux, and web.

AI & Agents Score 82/100 7 findings 138k/wk Cap. High
Tachibot npm
B
tachibot-mcp

TachiBot MCP: 65 AI tools, 12 providers. Multi-model orchestration (Perplexity, Grok, OpenAI, Gemini, Qwen, Kimi, MiniMax, DeepSeek, GLM, StepFun, ERNIE, local), YAML workflows, token-optimized profiles. Smart routing, parallel execution, jury system.

AI & Agents Score 82/100 18 findings 495/wk Cap. High
Agent Link npm
B
agent-link-mcp

MCP server for bidirectional AI agent collaboration — spawn and communicate with any AI coding agent CLI

AI & Agents Score 82/100 11 findings 34/wk Cap. High
Arc npm
B
arc-mcp

`plan_exact_design_extraction` 과 `extract_exact_design_document` 는 `@arc/design` exact-first pipeline 을 `arc-mcp`에서 바로 쓰기 위한 도구입니다.

AI & Agents Score 82/100 3 findings 14/wk Cap. Critical
Atabey npm
B
atabey-mcp

Atabey — AI Governance & Multi-Agent Platform / Orchestrator — MCP Server

AI & Agents Score 81/100 15 findings 24/wk Cap. High
Conductor npm
B
@useconductor/conductor

The AI Tool Hub — One MCP server. 255 tools. Every AI agent.

AI & Agents Score 81/100 23 findings 14/wk Cap. High
Nexus Mcp Agent npm
B
nexus-mcp-agent

Agentic OS MCP Server — 169 tools with on-demand loading (26 core), Streamable HTTP transport, background task engine, browser automation, TF-IDF semantic memory, multi-agent orchestration. Zero API keys.

AI & Agents Score 80/100 20 findings 73/wk Cap. Critical
Clawsouls npm
B
clawsouls-mcp

ClawSouls MCP Server — SoulScan, Soul Rollback, Swarm Memory, Persona Search & Install for AI agents

AI & Agents Score 80/100 4 findings 20/wk Cap. Critical
Kitty Hive Source verified npm
C
kitty-hive

MCP server for multi-agent collaboration — DM, tasks, workflow, federation

AI & Agents Score 79/100 9 findings 31/wk Cap. Critical
Playwright npm
C
playwright-mcp

Playwright integration for ModelContext

AI & Agents Score 78/100 3 findings 9.3k/wk Cap. High
Mcp Remote
C
https://mcp.redu.cloud/mcp

Agent-native cloud, EU-hosted. Provision VMs, networks & databases on redu.cloud via MCP.

AI & Agents Score 78/100 12 findings Cap. Critical
Covenant npm
C
@varun-ai07/covenant-mcp

COVENANT Protocol MCP Server — AI agent access to on-chain task marketplace

AI & Agents Score 77/100 11 findings 25/wk Cap. Critical
Agent Security Scanner npm
C
agent-security-scanner-mcp

AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools, and vulnerable code.

AI & Agents Score 76/100 24 findings 1.9k/wk Cap. High
Oioxo npm
C
oioxo-mcp

OIOXO — cut your AI bill by up to ~90%: it feeds Claude Code, Copilot, Cursor and any MCP agent only the relevant slice of your codebase instead of whole files. Also a private terminal coding agent (`oioxo code`, on-device with --local or any key). Runs o

AI & Agents Score 71/100 7 findings 15/wk Cap. High
Depwire Cli npm
D
depwire-cli

Dependency graph + 23 MCP tools for AI coding assistants. Impact analysis, health scoring, security scanner, agent coordination.

AI & Agents Score 64/100 9 findings 1.8k/wk Cap. Critical
Shellward npm
D
shellward

AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.

AI & Agents Score 60/100 18 findings 437/wk Cap. High
Infomaniak Mcp Agent npm
F
infomaniak-mcp-agent

Full unofficial agentic Infomaniak MCP server — guided automation of web hosting, mail, kDrive, domains and DNS

AI & Agents Score 56/100 2 findings 178/wk Cap. Critical
Rate-My-Agent Remote
F
https://mcp.rate-my-agent.com/mcp

Get matched with a top-rated, review-verified real estate agent in the US or Canada.

AI & Agents Score 47/100 3 findings Cap. Moderate