Agentic Wallet Guardian V3 runs on your own machine — the client starts it, so there is no endpoint to ping. 87 installs a week from pypi. Last commit 30 Aug 2026.
Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.
Today is the operative word: we check Agentic Wallet Guardian V3 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 agentic-wallet-guardian-v3 -- uvx agentic-wallet-guardian-mcp
{
"mcpServers": {
"agentic-wallet-guardian-v3": {
"args": [
"agentic-wallet-guardian-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.agentic-wallet-guardian-v3]
command = "uvx"
args = ["agentic-wallet-guardian-mcp"]
{
"mcpServers": {
"agentic-wallet-guardian-v3": {
"args": [
"agentic-wallet-guardian-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"agentic-wallet-guardian-v3": {
"args": [
"agentic-wallet-guardian-mcp"
],
"command": "uvx"
}
}
}
Action firewall for AI agents: blocks the wrong action before it runs, every verdict Ed25519-signed.
Decision-assurance for AI agents: an auditable action boundary + receipt before it acts.
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Authorize consequential AI agent actions before execution
Security suite for AI agents: flag drains, permit-phishing & risky actions before signing.
Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.
Deterministic multi-criteria decision analysis for AI agents — score, rank & explain options.
Answers built from our own checks of this server.