mcpbeat Sign in

Offense MCP Server

by offense-research Your server? Claim it
answering

Offense is answering right now. Last checked 13 min ago. It exposes 1 tools. Last commit 1 Nov 2026.

Security tools for coding agents: dependency advisory audits and evidence for remediation.

Uptime history 38 hours of history
38 hours agonow
100.0%
Uptime 24h
91 of 91 checks
1
Tools
read from the server
607 ms
Response time
average over 24h
47
Stars
last commit 1 Nov 2026

What the code does

We read the source, 16 h ago · tools taken from the live server · rules 995398eba69f

Capabilities

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.

    const child = spawn(argv[0], argv.slice(1), {
for (const name of ['candidate', 'output', 'candidate/test']) await mkdir(path.join(root, name), { recursive: true, mode: 0o777 });
        process = subprocess.Popen(command, cwd=app, env=environment(directory, port, token), stdin=subprocess.DEVNULL,
Builds a database query by concatenation offense/src/upgrade-routes.js:40, src/upgrade-routes.js:40
      ...rootUpdates.map(update => `Update the application declaration${update.workspace ? ` in ${update.workspace}` : ''} for ${update.name}${update.range ? ` (${update.range})` : ''} to allow ${update.targetVersion}.`)].join(' '),
Asks for container control access offense/tools/api-test.mjs:80
  return ['--host', 'unix:///var/run/docker.sock', 'run', '--name', name, '--rm', ...(detached ? ['--detach'] : ['--interactive']), '--pull', 'never',

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

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.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add offense --transport http https://offense.sh/mcp
Settings → Connectors → Add custom connector, then paste this address
https://offense.sh/mcp
~/.codex/config.toml
[mcp_servers.offense]
url = "https://offense.sh/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "offense": {
      "url": "https://offense.sh/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "offense": {
      "type": "http",
      "url": "https://offense.sh/mcp"
    }
  }
}

Available tools 1

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

offense
offense.audit_dependencies
Use Purple to audit sanitized npm/pnpm dependency metadata for known advisory matches and checked upgrade paths. Resume deferred targets with remediation.planning.next while retaining the full scan and coordinating plans across pages. Does not read source, run tests, edit files, confirm exploitability or use a model key.

Endpoints

URLTransportStateLatencyChecked
https://offense.sh/mcp streamable-http answering 418 ms 13 min ago

Alternatives to Offense

same job, measured the same way
Defenter Proxy
by defenter-ai

Real-time semantic security for AI coding agents and MCP tools

76 installs/wk local only
AgentDiet Coding Agent GitHub Repo, Dependency & License Security Auditor
by agentdiet

Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and supply-c.

2 tools answering
Depwire
by atef-ataya

Dependency graph + 24 MCP tools. Impact analysis, simulation, security, agent coordination

614 installs/wk local only
Security Intel MCP
by datakoot

CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.

5 tools answering
Vaultguard MCP
by kota1026

VaultGuard MCP Server - Yearn V3 / DeFi vault security and analysis tools for AI coding agents....

45 installs/wk local only
Agent Security
by mdfifty50-boop

Security scanning and threat detection for AI agents

61 installs/wk local only
Bridgeguard MCP
by kota1026

BridgeGuard MCP Server - Cross-chain bridge security audit tools for AI coding agents. Scan bri...

43 installs/wk local only
Apiiro Guardian Agent
by apiiro

Apiiro Application Security Posture Management (ASPM) tools for AI coding assistants.

answering

Offense — questions

Answers built from our own checks of this server.

What can Offense do?
It exposes 1 tools, read directly from the server on our last check. Among them: offense.audit_dependencies. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Offense working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 607 ms. The bar chart above shows every period we have measured.
How do I connect Offense?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Offense need an API key?
No. Offense completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 1 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Offense?
It answers our handshake in 607 ms on average, which is faster than 17% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Offense open source?
The code is open source: it is published under the Apache-2.0 licence, written in JavaScript and 47 stars on GitHub. The licence covers the code in the repository, not the hosted service at offense.sh, which runs on its operator's own terms.