Agentshield MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 77 installs a week from npm. Last commit 11 May 2026.
Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
What the code does
We read the source, 6 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
tbody.innerHTML = keyList.map(k => `<tr>
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add agentshield-mcp -e 'AGENTSHIELD_API_KEY=<AGENTSHIELD_API_KEY>' -- npx -y @eigenart/agentshield-mcp{
"mcpServers": {
"agentshield-mcp": {
"command": "npx",
"args": [
"-y",
"@eigenart/agentshield-mcp"
],
"env": {
"AGENTSHIELD_API_KEY": "<AGENTSHIELD_API_KEY>"
}
}
}
}[mcp_servers.agentshield-mcp]
command = "npx"
args = ["-y", "@eigenart/agentshield-mcp"]
env = { AGENTSHIELD_API_KEY = "<AGENTSHIELD_API_KEY>" }{
"mcpServers": {
"agentshield-mcp": {
"command": "npx",
"args": [
"-y",
"@eigenart/agentshield-mcp"
],
"env": {
"AGENTSHIELD_API_KEY": "<AGENTSHIELD_API_KEY>"
}
}
}
}{
"servers": {
"agentshield-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@eigenart/agentshield-mcp"
],
"env": {
"AGENTSHIELD_API_KEY": "<AGENTSHIELD_API_KEY>"
}
}
}
}Put your own value in place of
<AGENTSHIELD_API_KEY> (Your AgentShield API key. Sign up at https://agentshield.pro/signup (free tier, no credit card)).
The author’s registry entry marks it as required.
Alternatives to Agentshield MCP
same job, measured the same wayBrand-safe ad, email, product description, and social content production.
Social posts, ads and insights for e-commerce. One connection for your agent.
Request quotes for video, shooting, social media, ad media, design, web and events in Japan.
Crypto social intelligence from X and Telegram, plus the Elfa Auto condition engine
One connection for your agent to email, calendars, Drive, Slack, ads, payments, social and alerts.
Extracts verified emails, social links, 40+ tech stack signals, pricing tiers, and company summar.
A social network for AI agents: read communities, join, post, comment and vote in plain English.
Social listening for agents: brand mentions across 16 platforms, scored for relevance and intent
Agentshield MCP — questions
Answers built from our own checks of this server.