# Offense (remote · offense.sh)

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

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `offense.sh`: 71/100 (this document), [markdown](https://verifymcp.io/servers/offense-research-offense/offense.md), [page](https://verifymcp.io/servers/offense-research-offense/offense)

## Channel facts

- Endpoint: `https://offense.sh/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.7.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 272 tokens (~272/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Offense MCP server?

Offense is a hosted endpoint at https://offense.sh/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http offense-research-offense 'https://offense.sh/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "offense-research-offense": {
      "url": "https://offense.sh/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "offense-research-offense": {
      "type": "http",
      "url": "https://offense.sh/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.offense-research-offense]
url = "https://offense.sh/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "offense-research-offense": {
      "type": "remote",
      "url": "https://offense.sh/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add offense-research-offense --url 'https://offense.sh/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  offense-research-offense:
    url: "https://offense.sh/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "offense-research-offense": {
      "Transport": "http",
      "Url": "https://offense.sh/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add offense-research-offense -t streamable-http -u 'https://offense.sh/mcp'
```

### Other

```json
{
  "mcpServers": {
    "offense-research-offense": {
      "type": "http",
      "url": "https://offense.sh/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-31 (score 69)

First indexed and scored.

## MCP tools (1)

### `offense.audit_dependencies` (~189 tokens)

Offense dependency audit

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.

Input parameters:

- `files` (array, required): Locally sanitized npm v2/v3 or pnpm v6/v9 lockfile metadata. The server cannot read local paths. Do not send source, credentials or registry URLs.
- `planLimit` (integer): Maximum affected package/version pairs to plan in this response, highest severity first. Zero scans only. Follow remediation.planning.next for remaining targets; omitted or failed paths remain explic…
- `planning` (object): Use remediation.planning.next unchanged with the same sanitized files to continue planning. This checks only selected planning targets; retain and merge the original full advisory report.

Output parameters:

- `capability`
- `coverage` (object)
- `findings` (array)
- `providers` (array)
- `remediation` (object)
- `schemaVersion`
- `status`
- `summary` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/offense-research-offense/offense#diagnostics

## Score history

- 2026-11-04: 71
- 2026-11-03: 70
- 2026-11-02: 70
- 2026-11-01: 69
- 2026-10-31: 69

## Common questions

### What is the Offense MCP server?

Offense is an MCP server listed in the public MCP registry as io.github.offense-research/offense. Security tools for coding agents: dependency advisory audits and evidence for remediation. This page covers its hosted endpoint (https://offense.sh/mcp).

### Is the Offense MCP server safe to use?

Offense scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Offense MCP server expose?

Offense exposes 1 tool: offense.audit_dependencies. Their descriptions and schemas cost roughly 189 tokens of context every time the server is loaded.

### Does the Offense MCP server require authentication?

No. We connected to Offense without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Offense MCP server still maintained?

Offense is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://offense.sh/mcp
- Repository: https://github.com/offense-research/offense
- Website: https://offense.sh/
- Changelog RSS feed: https://verifymcp.io/servers/offense-research-offense/offense.xml
- Changelog JSON feed: https://verifymcp.io/servers/offense-research-offense/offense.json
- HTML version of this page: https://verifymcp.io/servers/offense-research-offense/offense