Tripwire runs on your own machine — the client starts it, so there is no endpoint to ping. 47 installs a week from npm. Last commit 12 Jun 2026.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Today is the operative word: we check Tripwire 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 tripwire -- npx -y tripwire-mcp
{
"mcpServers": {
"tripwire": {
"command": "npx",
"args": [
"-y",
"tripwire-mcp"
]
}
}
}
[mcp_servers.tripwire]
command = "npx"
args = ["-y", "tripwire-mcp"]
{
"mcpServers": {
"tripwire": {
"command": "npx",
"args": [
"-y",
"tripwire-mcp"
]
}
}
}
{
"servers": {
"tripwire": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tripwire-mcp"
]
}
}
}
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Agent security pre-checks: prompt-injection scan, MCP tool-poisoning scan, x402 endpoint check.
Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
Answers built from our own checks of this server.