AI Adoption Controls Framework (AACF) MCP server
com.adriansaxton/aacfadriansaxton.comstreamable-httpv1.2.1Scanned
Read-only AI Adoption Controls Framework: controls, Level 3 criteria, standards cross-references
8 tools: 8 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
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.
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 AI Adoption Controls Framework (AACF) MCP server can do
The AI Adoption Controls Framework (AACF) MCP server is published by adriansaxton.com, a domain the MCP Registry verified. It has 8 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
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 1.2.1.
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.
8 tools
Only reads 8Show 8 read-only tools
get_assessment_questionsQuestions, evidence and the applicable Level 3 criteria for one domain (or a published profile), for a self-assessment the user's own assistant runs.No findings
Why it is in this group
- The name "get_assessment_questions" says "get": a word for reading.
Description, as the server wrote it Questions, evidence and the applicable Level 3 criteria for one domain (or a published profile), for a self-assessment the user's own assistant runs. Pass the overlays that apply to the organisation. Answers are never sent to this server. Call with no domain to list the domains.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_controlOne control in full: objective, rationale, level descriptors 1 to 5, Level 3 criteria (with the overlays they apply to), questions, evidence, guidance, owners, dependencies and cro…No findings
Why it is in this group
- The name "get_control" says "get": a word for reading.
Description, as the server wrote it One control in full: objective, rationale, level descriptors 1 to 5, Level 3 criteria (with the overlays they apply to), questions, evidence, guidance, owners, dependencies and cross-references.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_framework_infoVersion, scale, overlays, owner roles, lifecycle stages, the cross-referenced standards and how to cite AACF.No findings
Why it is in this group
- The name "get_framework_info" says "get": a word for reading.
Description, as the server wrote it Version, scale, overlays, owner roles, lifecycle stages, the cross-referenced standards and how to cite AACF. Call this first.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_mappingReverse lookup: the controls that address an item of a standard, with strength (direct or partial) and confidence.No findings
Why it is in this group
- The name "get_mapping" says "get": a word for reading.
Description, as the server wrote it Reverse lookup: the controls that address an item of a standard, with strength (direct or partial) and confidence. A ref that is a prefix (for example 6.1) returns every item under it.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_scoring_rulesThe assessor rulebook: scope, statuses, how to place a level (Level 3 needs every applicable criterion met; never round up), evidence, targets and how to report.No findings
Why it is in this group
- The name "get_scoring_rules" says "get": a word for reading.
Description, as the server wrote it The assessor rulebook: scope, statuses, how to place a level (Level 3 needs every applicable criterion met; never round up), evidence, targets and how to report.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_standard_coverageEvery cross-referenced item of one standard, the controls covering each, and summary counts.No findings
Why it is in this group
- The name "get_standard_coverage" says "get": a word for reading.
Description, as the server wrote it Every cross-referenced item of one standard, the controls covering each, and summary counts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_domainsEvery domain with its summary and the ID and title of each control in it.No findings
Why it is in this group
- The name "list_domains" says "list": a word for reading.
Description, as the server wrote it Every domain with its summary and the ID and title of each control in it.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_controlsFind controls by words in their title, objective, rationale, criteria or questions, optionally filtered by domain, overlay, owner role or lifecycle stage.No findings
Why it is in this group
- The name "search_controls" says "search": a word for reading.
Description, as the server wrote it Find controls by words in their title, objective, rationale, criteria or questions, optionally filtered by domain, overlay, owner role or lifecycle stage. Returns summaries; use get_control for detail.
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 16, 2026, 14:18 UTC, unchanged since Nov 16, 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 1.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http aacf https://aacf.adriansaxton.com/mcpclaude mcp add --transport http aacf https://aacf.adriansaxton.com/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__aacf__get_framework_info",
"mcp__aacf__list_domains",
"mcp__aacf__get_control",
"mcp__aacf__search_controls",
"mcp__aacf__get_mapping",
"mcp__aacf__get_standard_coverage",
"mcp__aacf__get_assessment_questions",
"mcp__aacf__get_scoring_rules"
],
"ask": [],
"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 aacf. 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/com.adriansaxton/aacf/verify?hash=ae4af8de233e9ce241a95fda05d3f68bedbc09020c9f4a3bbd7e17a7844d7dbf" | jq -e '.changed == false'Pinned hash ae4af8de233e, from Nov 15, 2026, 21:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.adriansaxton/aacf/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.adriansaxton/aacf)Source: MCP Registry · repository. Synced Nov 15, 2026, 22:17 UTC.
AI Adoption Controls Framework (AACF) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AI Adoption Controls Framework (AACF) MCP server safe?
- No scan can promise that. What its definitions show: 8 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 AI Adoption Controls Framework (AACF) MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AI Adoption Controls Framework (AACF) 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 AI Adoption Controls Framework (AACF) MCP server have?
- 8 tools: 8 read. get_framework_info, list_domains, get_control, search_controls, get_mapping, get_standard_coverage, get_assessment_questions and get_scoring_rules.
Does the AI Adoption Controls Framework (AACF) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AI Adoption Controls Framework (AACF) MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AI Adoption Controls Framework (AACF) MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.