agentmods.dev

maxwell-defense

maxwell-defense is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from jdhart81/viridis-agent-fleet. Its token cost is not measured, scanned A, original, Apache-2.0.

A remote service that models proof-of-work policy and response time for AI agents. It charges $1 in USDC for a rehearsal and does not provide protection while the agent runs.

In plain words
What is it for?
It is for rehearsing or evaluating proof-of-work policies and their latency for agents.
Why use it?
It lets users examine policy and latency trade-offs without treating the model as live security enforcement.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

One of 32 entries in server.json upstream. Installing this one merges just its entry into your config; the other 31 are separate, each on its own page.

not rated 0repo today A scan tokens not measured original Apache-2.0

Good fit It is for rehearsing or evaluating proof-of-work policies and their latency for agents.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/jdhart81/viridis-agent-fleet/agent-arbitration-agent-maxwell-defense
View source ↗ jdhart81/viridis-agent-fleet mcp.viridis-security.com
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/jdhart81/viridis-agent-fleet

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for maxwell-defense

README.md
[![agentmods](https://agentmods.dev/badge/mcp/jdhart81/viridis-agent-fleet/agent-arbitration-agent-maxwell-defense/github.svg)](https://agentmods.dev/mcp/jdhart81/viridis-agent-fleet/agent-arbitration-agent-maxwell-defense)
Your own site
<a href="https://agentmods.dev/mcp/jdhart81/viridis-agent-fleet/agent-arbitration-agent-maxwell-defense"><img src="https://agentmods.dev/badge/mcp/jdhart81/viridis-agent-fleet/agent-arbitration-agent-maxwell-defense/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for maxwell-defense

Your own site · 80×15
<a href="https://agentmods.dev/mcp/jdhart81/viridis-agent-fleet/agent-arbitration-agent-maxwell-defense"><img src="https://agentmods.dev/badge/mcp/jdhart81/viridis-agent-fleet/agent-arbitration-agent-maxwell-defense.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

maxwell-defense scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

deploy/mcp-publish-github/agent-arbitration-agent/server.json · 6 lines

What it actually says

{
  "maxwell-defense": {
    "url": "https://mcp.viridis-security.com/maxwell-defense/mcp",
    "type": "streamable-http"
  }
}
Same file

What else server.json configures

This page is one entry in a file that holds 32. Installing the file brings all of them; each is measured and scanned on its own page.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 24d ago First seen · 6 lines scan A 294054864777

Subscribe to this mod's changes

maxwell-defense is an MCP server published in the GitHub repository jdhart81/viridis-agent-fleet (0 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.

Building agentsSecurityagent-securityai-agentsdeveloper-toolsmcpmcp-serverpolicy-as-code
Related

Other mcp servers, from other repositories

assay-mcp-server

MCP server "assay-mcp-server" as configured in Rul1an/assay. Launched with https://github.com/Rul1an/assay/releases/download/v6.9.0/assay-mcp-server-v6.9.0.

Rul1an/assay · not measured

assay

MCP server "assay" as configured in Rul1an/assay. Launched with assay-mcp-server --policy-root ..

Rul1an/assay · not measured

payment-guard-mcp

Pre-send risk check for AI agents that move money — screen an address or payment URL before sending. Runs locally from the payment-guard-mcp npm package.

mlawsonking/MCP · not measured

agent-firewall-mcp

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets. Runs locally from the agent-firewall-mcp npm package.

mlawsonking/MCP · not measured

agent-guards

All six agent guard suites in one local MCP server, with optional cloud intelligence. Runs locally from the agent-guards npm package.

mlawsonking/MCP · not measured

code-guard-mcp

Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization. Runs locally from the @mlawsonking/code-guard-mcp npm package.

mlawsonking/MCP · not measured