AgentShield runs on your own machine — the client starts it, so there is no endpoint to ping. 20 installs a week from npm.
Smart contract security for AI agents — verify, monitor, freeze, x402 payments
Today is the operative word: we check AgentShield every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 -- npx -y agentshield-protocol
{
"mcpServers": {
"agentshield": {
"args": [
"-y",
"agentshield-protocol"
],
"command": "npx"
}
}
}
[mcp_servers.agentshield]
command = "npx"
args = ["-y", "agentshield-protocol"]
{
"mcpServers": {
"agentshield": {
"args": [
"-y",
"agentshield-protocol"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agentshield": {
"args": [
"-y",
"agentshield-protocol"
],
"command": "npx"
}
}
}
Process management and monitoring for AI agents with strict security boundaries
13 tools for AI agents: scrape, crawl, extract, map, search, papers, batch, research, monitor.
MCP server for Site Spy — lets AI agents monitor websites for changes
Evidence-traced codebase understanding and security scanning for AI agents over MCP.
MCP server for Docker — containers, health checks, Compose, logs, monitoring for AI agents
PlatformIO for AI agents: build, flash, serial monitor, tests, crash decoding, size reports.
Prediction-market monitoring, AI-agent context, and recurring x402 machine checks.
Verifiable crypto signals, recorded history and always-on monitoring for AI agents via x402 on Base.
Answers built from our own checks of this server.