Agentguard runs on your own machine — the client starts it, so there is no endpoint to ping. 40 installs a week from npm. Last commit 13 Jun 2026.
Network-egress firewall for agent tools: check URLs against a declarative policy.
Today is the operative word: we check Agentguard 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 agentguard -- npx -y @mukundakatta/agentguard-mcp
{
"mcpServers": {
"agentguard": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentguard-mcp"
]
}
}
}
[mcp_servers.agentguard]
command = "npx"
args = ["-y", "@mukundakatta/agentguard-mcp"]
{
"mcpServers": {
"agentguard": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentguard-mcp"
]
}
}
}
{
"servers": {
"agentguard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentguard-mcp"
]
}
}
}
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
Free pre-action policy checks and data cleaning for autonomous AI agents.
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt
Three-layer firewall for MCP: content, egress and action policy. Proxy or server.
Local agent spend-policy checks. No funds, keys, payment authority, or network access.
Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.
Answers built from our own checks of this server.