Offense MCP server
io.github.offense-research/offenseoffense-researchstreamable-httpv0.7.0Scanned
Security tools for coding agents: dependency advisory audits and evidence for remediation.
1 tool: 1 change things.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- 1 finding
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
1 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Offense MCP server can do
The Offense MCP server is published by the GitHub account offense-research. It has 1 tool. It can create or change data (1 tool: offense.audit_dependencies), but cannot delete data. None of its tools only reads.
1 tool brings in text other people can write (offense.audit_dependencies).
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Last scanned Oct 31, 2026, version 0.7.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
1 tool
Changes things 1Claude Code: ask
offense.audit_dependenciesUse Purple to audit sanitized npm/pnpm dependency metadata for known advisory matches and checked upgrade paths.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.files.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.files.description: "...t read local paths. Do not send source, credentials or registry URLs."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 15, 2026, 13:21 UTC, unchanged since Nov 15, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 404
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: initialize answered HTTP 404.
Posture changes
- Nov 15, 2026
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
The input schema at properties.files.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.files.description: "...t read local paths. Do not send source, credentials or registry URLs."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 1 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 0.7.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http offense https://offense.sh/mcpclaude mcp add --transport http offense https://offense.sh/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__offense__offense_audit_dependencies"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as offense. Review it before you use it.
Capability tags behind 1 rule
- mcp__offense__offense_audit_dependencies untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.offense-research/offense/verify?hash=04dc928f1cadb062792077fe74285f1b2634a2896b49a28b53ef77a69b1ec163" | jq -e '.changed == false'Pinned hash 04dc928f1cad, from Oct 31, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.offense-research/offense/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.offense-research/offense)Source: MCP Registry · repository. Synced Oct 31, 2026, 01:17 UTC.
Offense MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Offense MCP server safe?
- No scan can promise that. What its definitions show: 1 tool, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Offense MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Offense MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Offense MCP server have?
- 1 tool: 1 write. offense.audit_dependencies.
Does the Offense MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Offense MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Offense MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 31, 2026.