Arquestra Audit

io.github.pablo-ramossanchez/arquestra-auditpablo-ramossanchezstreamable-httpv0.8.1Scanned 56 minutes ago

Audit a data file before publishing: one light per figure. Your data never reaches the server.

5 tools: 3 change things and 2 only read.

Reads private data · 1
Reads text others write · 0
Can send data out · 0
2 findings

Anlyon alternative

3 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 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 →

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.

5 tools

Changes things 3Creates or changes something that can be changed back.Claude Code: ask

example_auditsPublished example audits, such as the AI Project Radar, and how the audit works.No findings
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.
Description, as the server wrote it
Published example audits, such as the AI Project Radar, and how the audit works. With no arguments: the overview and the list of examples. With a name: one example, result by result (level filters by light). With a name and an id: one result with every reason and what to change. They are not the person's data.
Annotations the server declares
- title: What the audit is, with worked examples
- readOnlyHint: true
- openWorldHint: false
measure_in_appOpens the audit panel in the chat.1 finding
Why it is in this group
- The description's first verb is "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "measure_in_app" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"openWorldHint":false}; The description's first verb is "open": a word for a change.
  What this check looks for
Description, as the server wrote it
Opens the audit panel in the chat. Without a spec, the panel receives the person's file, reads it in their browser and returns a profile of it: per column its kind, empty cells, distinct values, the values of categories with their counts, the range of numbers and dates, and the first rows. With a confirmed spec, the panel measures that same file in the browser with measure.py and shows one light per result. The file is not sent to this server.
Annotations the server declares
- title: Measure the person's file inside the audit panel
- readOnlyHint: true
- openWorldHint: false
start_auditProposes how to read a data file for an audit, from its column names (optionally a type and one example value each) and the results the person wants to publish.1 finding
Why it is in this group
- The name "start_audit" says "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "start_audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "start_audit" says "start": a word for a change.
  What this check looks for
Description, as the server wrote it
Proposes how to read a data file for an audit, from its column names (optionally a type and one example value each) and the results the person wants to publish. Returns a proposed spec (the role of each column, each result written as a claim), how claims are written, the catalog of checks and the points the person has to confirm. It receives no rows.
Annotations the server declares
- title: Start an audit of the person's data
- readOnlyHint: true
- openWorldHint: false

Only reads 2Looks things up and changes nothing.Show 2 read-only tools

prepare_scriptReturns measure.py with a confirmed spec written in: a fixed Python script (standard library, no network, fixed seeds) that counts what each check needs from a data file and prints…Reads private dataNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "file": it reads files.
Description, as the server wrote it
Returns measure.py with a confirmed spec written in: a fixed Python script (standard library, no network, fixed seeds) that counts what each check needs from a data file and prints those counts with its own fingerprint and no rows. Reads .csv or .json. If the spec has errors, returns the errors instead.
Annotations the server declares
- title: Get the script that measures the data
- readOnlyHint: true
- openWorldHint: false
show_auditTurns the output of measure.py into one light per result (red, amber or green, with its reasons), after checking that the output comes from the unchanged script and from the given …No findings
Why it is in this group
- The name "show_audit" says "show": a word for reading.
Description, as the server wrote it
Turns the output of measure.py into one light per result (red, amber or green, with its reasons), after checking that the output comes from the unchanged script and from the given spec. Shows the lights in the chat and returns them, with a link to the same view on arquestra.dev that carries only codes. Stores nothing.
Annotations the server declares
- title: Show the lights of the person's audit
- 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 untrusted-input or outbound.

Reads private data1: Reads files, mail, messages, databases, secrets, calendars or repositories.; prepare_script
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.

Findings

Matches of fixed checks, with the text they matched.

2 warn

Warnstart_audit
The server marks "start_audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "start_audit" says "start": a word for a change.
What this check looks for
Warnmeasure_in_app
The server marks "measure_in_app" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The description's first verb is "open": a word for a change.
What this check looks for

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.

All changes to this server

Install

Pinned to version 0.8.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http arquestra-audit https://arquestra.dev/api/mcp/audit

claude mcp add --transport http arquestra-audit https://arquestra.dev/api/mcp/audit

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__arquestra-audit__prepare_script",
      "mcp__arquestra-audit__show_audit"
    ],
    "ask": [
      "mcp__arquestra-audit__start_audit",
      "mcp__arquestra-audit__measure_in_app",
      "mcp__arquestra-audit__example_audits"
    ],
    "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 arquestra-audit. Review it before you use it.

Capability tags behind 1 rule

mcp__arquestra-audit__prepare_script private-data

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://anlyon.dev/api/v1/servers/io.github.pablo-ramossanchez/arquestra-audit/verify?hash=91e381c2273871389570623f6c4437c1d12513ea34672a45b5f74ae21f02be45" | jq -e '.changed == false'

Pinned hash 91e381c22738, from Nov 3, 2026, 14:18 UTC.

Watch

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

https://anlyon.dev/servers/io.github.pablo-ramossanchez/arquestra-audit/changes.xml

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

Badge

[![anlyon.dev](https://anlyon.dev/badge/io.github.pablo-ramossanchez/arquestra-audit.svg)](https://anlyon.dev/servers/io.github.pablo-ramossanchez/arquestra-audit)

Source: MCP Registry · repository. Synced Nov 3, 2026, 14:18 UTC.