Maxwell Defense is answering right now. Last checked 14 min ago. It exposes 2 tools. Last commit 18 Sep 2026.
Model proof-of-work policy and latency for AI agents. $1 USDC rehearsal; no runtime protection.
We read the source, 22 h ago · tools taken from the live server · rules 3dff92dd89df
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.
state = pickle.loads(row[0])
r = subprocess.run([sys.executable, "-c", code], capture_output=True, text=True)
$("kpis").innerHTML = cells.map(([l,v,d]) =>
self.environ = dict(os.environ if environ is None else environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add maxwell-defense --transport http https://mcp.viridis-security.com/maxwell-defense/mcp
{
"mcpServers": {
"maxwell-defense": {
"url": "https://mcp.viridis-security.com/maxwell-defense/mcp"
}
}
}
[mcp_servers.maxwell-defense]
url = "https://mcp.viridis-security.com/maxwell-defense/mcp"
{
"mcpServers": {
"maxwell-defense": {
"url": "https://mcp.viridis-security.com/maxwell-defense/mcp"
}
}
}
{
"mcpServers": {
"maxwell-defense": {
"url": "https://mcp.viridis-security.com/maxwell-defense/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
describe_agent
rehearse_defense
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.viridis-security.com/maxwell-defense/mcp | streamable-http | answering | 380 ms | 14 min ago |
Model Context Protocol server for Retain: let AI agents query churn risk and act on retention.
Runtime authorization for AI agents and smart contracts via an immutable on-chain policy registry
Pay-per-call web search, translation and research jobs for AI agents. USDC on Base, no account.
Personality Runtime for AI agents — persistent memory, personality, and relationships via MCP
Universal memory runtime for AI agents — episodic, semantic, and procedural memory.
Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects
Laviya AI Orchestration MCP runtime for IDE and agent integrations.
Vantio Gate — Policy Latch dry-run evaluate for agents. No live enforce from MCP.
Answers built from our own checks of this server.