Skip to content

Auditon security assessments MCP server

co.auditon/assessmentsauditon.costreamable-httpv1.0.0Scanned

Read-only access to your Auditon vulnerability scans: findings, endpoints, reports and changes.

6 tools: 6 only read.

Tools: 0 delete, 0 irreversible, 0 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 4
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Auditon security assessments MCP server can do

The Auditon security assessments MCP server is published by auditon.co, a domain the MCP Registry verified. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

4 tools bring in text other people can write (list_scans, get_report, list_findings and 1 more); 4 tools can send data out of your system (list_scans, get_report, list_findings and 1 more).

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 12, 2026, version 1.0.0.

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.

6 tools

Only reads 6Show 6 read-only tools
  • compare_scansWhat changed on an endpoint between two scans: appeared, resolved, not reassessed (the check did not complete, so status is unknown) and severity changes.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "compare_scans" says "compare": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.endpoint), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    What changed on an endpoint between two scans: appeared, resolved, not reassessed (the check did not complete, so status is unknown) and severity changes. Without scan ids, compares the endpoint's two most recent scans.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_findingFull detail for one finding: description, impact, remediation, references, evidence, analyst decision and its history across scans.No findings

    Why it is in this group

    • The name "get_finding" says "get": a word for reading.
    Description, as the server wrote it
    Full detail for one finding: description, impact, remediation, references, evidence, analyst decision and its history across scans.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_reportOne scan as structured data: rating, coverage gaps, findings, items requiring verification, accepted risks, dismissed false positives and passed controls.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_report" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.endpoint), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    One scan as structured data: rating, coverage gaps, findings, items requiring verification, accepted risks, dismissed false positives and passed controls. Read "interpretation" before drawing conclusions. Set detail=true for descriptions and remediation.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_endpointsHosts assessed in this workspace, with open findings by severity and the most recent scan.No findings

    Why it is in this group

    • The name "list_endpoints" says "list": a word for reading.
    Description, as the server wrote it
    Hosts assessed in this workspace, with open findings by severity and the most recent scan. Start here.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_findingsCurrent findings across all scans, most severe first.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "list_findings" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.endpoint), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Current findings across all scans, most severe first. Defaults to open findings; potential (unconfirmed) matches are included and marked by assurance.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_scansScans, newest first: type, status, rating and coverage.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "list_scans" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.endpoint), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Scans, newest first: type, status, rating and coverage. With an endpoint, rating, findings and coverage are for that endpoint only.

    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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:32 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
0
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

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http assessments https://auditon.co/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http assessments https://auditon.co/mcp --header 'Authorization: <your-authorization>'

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__assessments__list_endpoints",
      "mcp__assessments__get_finding"
    ],
    "ask": [
      "mcp__assessments__list_scans",
      "mcp__assessments__get_report",
      "mcp__assessments__list_findings",
      "mcp__assessments__compare_scans"
    ],
    "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 assessments. Review it before you use it.

Capability tags behind 4 rules
  • mcp__assessments__list_scans untrusted-input, outbound
  • mcp__assessments__get_report untrusted-input, outbound
  • mcp__assessments__list_findings untrusted-input, outbound
  • mcp__assessments__compare_scans untrusted-input, outbound

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/co.auditon/assessments/verify?hash=51e15fed81ebbd5d539006f4e896deedae3248b93f2ec3c2aaaee9cb911531a5" | jq -e '.changed == false'

Pinned hash 51e15fed81eb, from Nov 12, 2026, 09:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/co.auditon/assessments/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for co.auditon/assessments
[![Anlyon Radar](https://radar.anlyon.com/badge/co.auditon/assessments.svg)](https://radar.anlyon.com/servers/co.auditon/assessments)

Source: MCP Registry. Synced Oct 21, 2026, 17:46 UTC.

Auditon security assessments MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Auditon security assessments MCP server safe?

No scan can promise that. What its definitions show: 6 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the Auditon security assessments MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Auditon security assessments 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 Auditon security assessments MCP server have?

6 tools: 6 read. list_endpoints, list_scans, get_report, list_findings, get_finding and compare_scans.

Does the Auditon security assessments MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Auditon security assessments MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): list_scans, get_report, list_findings and compare_scans.

Has the Auditon security assessments MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.