code-auditor-mcp server
io.github.BenAHammond/code-auditor-mcpBenAHammondstreamable-httpv5.0.2Scanned
Enforces architectural invariants and code quality rules inside your AI agent's edit loop.
4 tools: 1 can delete or cancel things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the code-auditor-mcp server can do
The code-auditor-mcp server is published by the GitHub account BenAHammond. It has 4 tools. It can delete or cancel things (1 tool: request_rule). 3 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 5.0.2.
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.
4 tools
Deletes or cancels 1Claude Code: deny
request_ruleRequest a new Code Auditor rule.No findings
Why it is in this group
- The name "request_rule" says "request": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Request a new Code Auditor rule. Call lookup_rule or explain_symptom first to confirm no existing rule covers it. Provide a minimal example that should be flagged and a corrected example that should not. Reduce both to the smallest code that shows the difference, and remove secrets and proprietary identifiers. Returns a receipt id.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
Only reads 3Show 3 read-only tools
explain_symptomMap a natural-language symptom (e.g.No findings
Why it is in this group
- The name "explain_symptom" says "explain": a word for reading.
Description, as the server wrote it Map a natural-language symptom (e.g. 'my app is slow', 'hardcoded password', 'infinite react loop') to the relevant Code Auditor rule(s) and their fixes. Call this when a user describes a problem rather than naming a rule.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_install_commandsReturn the exact install commands for Code Auditor for a given AI agent.No findings
Why it is in this group
- The name "get_install_commands" says "get": a word for reading.
Description, as the server wrote it Return the exact install commands for Code Auditor for a given AI agent. Call this when a user asks how to install Code Auditor, or asks for the command for a specific agent (claude, cursor, codex, gemini, agents, zcode, or all).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
lookup_ruleReturn the rule kind, description, default severity, detection method, and threshold for a given Code Auditor rule or analyzer.No findings
Why it is in this group
- The name "lookup_rule" says "lookup": a word for reading.
Description, as the server wrote it Return the rule kind, description, default severity, detection method, and threshold for a given Code Auditor rule or analyzer. Call this when a user asks what a specific rule does (e.g. import-ban, sql-injection, n+1).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 20, 2026, 18:56 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 destructive). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.codeauditormcp.com/api/mcp: tools/list returned 4 tools to an anonymous client, including request_rule (destructive)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 5.0.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http code-auditor https://www.codeauditormcp.com/api/mcpclaude mcp add --transport http code-auditor https://www.codeauditormcp.com/api/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": [
"mcp__code-auditor__get_install_commands",
"mcp__code-auditor__lookup_rule",
"mcp__code-auditor__explain_symptom"
],
"ask": [],
"deny": [
"mcp__code-auditor__request_rule"
]
}
}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 code-auditor. Review it before you use it.
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.BenAHammond/code-auditor-mcp/verify?hash=d6e69d5c721f969388e85bbca281c568d40e08906df9dec09d5ab59bc8fa43b7" | jq -e '.changed == false'Pinned hash d6e69d5c721f, from Nov 15, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.BenAHammond/code-auditor-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.BenAHammond/code-auditor-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:14 UTC.
code-auditor-mcp server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the code-auditor-mcp server safe?
- No scan can promise that. What its definitions show: 4 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the code-auditor-mcp server delete data?
- Yes. 1 tool can delete, cancel or revoke something: request_rule.
Can the code-auditor-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 code-auditor-mcp server have?
- 4 tools: 1 destructive, 3 read. request_rule, get_install_commands, lookup_rule and explain_symptom.
Does the code-auditor-mcp server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the code-auditor-mcp server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the code-auditor-mcp server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.