# io.github.acfstandard/acf-mcp (npm · acf-mcp)

Official ACF® MCP server: Agentic Commerce Framework® governance copilot for AI assistants.

- Trust score: 59/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `acf-mcp`: 59/100 (this document), [markdown](https://verifymcp.io/servers/acfstandard-acf-mcp/acf-mcp.md), [page](https://verifymcp.io/servers/acfstandard-acf-mcp/acf-mcp)

## Channel facts

- Registry: `npm`
- Package: `acf-mcp`
- Version: `2.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 80/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 58 of 154 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 3725 tokens (~40/item across 92 items; 13 tools + 79 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.acfstandard/acf-mcp server?

io.github.acfstandard/acf-mcp runs locally as an npm package, launched with npx -y acf-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add acfstandard-acf-mcp -- npx -y acf-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "acfstandard-acf-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "acf-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "acfstandard-acf-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "acf-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add acfstandard-acf-mcp -- npx -y acf-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "acfstandard-acf-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "acf-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add acfstandard-acf-mcp --command npx --arg -y --arg acf-mcp
```

### Hermes

```yaml
mcp_servers:
  acfstandard-acf-mcp:
    command: "npx"
    args: ["-y", "acf-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "acfstandard-acf-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "acf-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add acfstandard-acf-mcp -t stdio -c npx -a -y acf-mcp
```

### Other

```json
{
  "mcpServers": {
    "acfstandard-acf-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "acf-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 57)

First indexed and scored.

## MCP tools (13)

### `acf.search` (~80 tokens)

When you don't know which ACF® resource is most relevant to the situation at hand (a question, a regulator request, a board challenge…), search the full ACF® corpus and rank candidate resources by relevance.

Input parameters:

- `limit` (integer)
- `locale` (string)
- `query` (string, required)
- `scope` (string)

### `acf.fiche.lookup` (~82 tokens)

When facing a specific governance question (defining an agent's mandate, designing a kill switch, building a decision register…), retrieve the canonical ACF® methodological card that applies: with its example, its mapping to principles and its related cards.

Input parameters:

- `code` (string, required)
- `include_frontmatter` (boolean)
- `locale` (string)

### `acf.regulation.article` (~108 tokens)

When a regulator, an auditor or a board references a specific article (AI Act Art. 9, GDPR Art. 35, DORA Art. 28, NIS2 Art. 21, ISO 42001 §6…), get the verified text and its operational translation into the ACF® framework: which principles it activates and which fiches operationalise it.

Input parameters:

- `article` (string, required)
- `locale` (string)
- `regulation` (string, required)

### `acf.glossary.define` (~72 tokens)

When governance vocabulary becomes ambiguous (what is a DDAO? what does Decision Sovereignty exactly mean? what separates co-decision from supervised autonomy?), get the canonical ACF® definition and its connection to the rest of the doctrine.

Input parameters:

- `locale` (string)
- `term` (string, required)

### `acf.cite` (~78 tokens)

When writing a thesis, a regulatory filing, a board memo or an academic paper that needs to reference ACF®, produce a properly formatted citation in the requested style (APA, MLA, Chicago, ISO 690, BibTeX).

Input parameters:

- `locale` (string)
- `style` (string)
- `uri` (string, required)

### `acf.classify-agent` (~214 tokens)

When a system owner needs a first-pass governance qualification of an AI agent before go-live: what autonomy level it likely operates at, what risk class it likely carries, what regulations apply, what controls to put in place, who should sign off: get one structured preliminary assessment covering all five questions in a single call. Input kept deliberately simple (10 qualified fields); output is structured for human review, not for autonomous regulatory decision-making.

Input parameters:

- `ai_act_triggers` (array)
- `decisions_taken` (array, required)
- `description` (string, required)
- `external_actions` (string, required)
- `financial_exposure` (string, required)
- `gpai_used` (boolean, required)
- `human_approval_required` (string, required)
- `jurisdiction` (array)
- `locale` (string)
- `name` (string, required)
- `personal_data_level` (string, required)
- `processing_purposes` (array)
- `sector` (string)
- `usage_audience` (string, required)

### `acf.advisor` (~118 tokens)

When a user describes a real AI use case and needs a structured ACF® governance assessment in return: which principles fire, which autonomy level fits, which regulatory obligations apply, which fiches to mobilise in what order, what are the first operational actions, what are the operational risks. This is the conversion tool: from documentation library to governance advisor.

Input parameters:

- `case_description` (string, required)
- `deployment_scale` (string)
- `jurisdiction` (string)
- `locale` (string)
- `sector` (string)

### `acf.assess-autonomy` (~124 tokens)

When deciding how much autonomy to grant an agent: should it propose, decide or execute? what triggers human review? what is the kill switch design?: get a first-pass assessment grounded in the 4 ACF® autonomy levels with explicit go/no-go criteria, gating thresholds, and uncertainty signalling for human review.

Input parameters:

- `agent_description` (string, required)
- `audit_requirements` (string, required)
- `human_in_loop_cost` (string)
- `intended_actions` (array, required)
- `locale` (string)
- `reversibility` (string, required)

### `acf.identify-governance-gaps` (~107 tokens)

When auditing your current AI governance setup: what does ACF® suggest you should have that you don't?: get a first-pass gap analysis across the 4 ACF® principles, prioritised by criticality, with remediation actions, quick wins, and explicit uncertainty signalling on which gaps were inferred vs declared.

Input parameters:

- `current_inventory` (object, required)
- `current_processes` (array, required)
- `locale` (string)
- `sector` (string)

### `acf.map-ai-act-obligations` (~170 tokens)

When a system has been preliminarily qualified as high-risk and you need the exhaustive list of AI Act obligations that apply: Art. 9 risk management, Art. 10 data, Art. 11 docs, Art. 12 logs, Art. 13 transparency, Art. 14 human oversight, Art. 15 robustness, GPAI Art. 51-55: get the full obligation set structured by lifecycle phase (pre-go-live / continuous / on-incident) with deadlines (incl. Digital Omnibus deferrals) and ACF® operational translation.

Input parameters:

- `annex` (string, required)
- `gpai_used` (boolean)
- `locale` (string)
- `provider_or_deployer` (string, required)
- `use_case` (string, required)

### `acf.assign-ddao-controls` (~123 tokens)

When a DDAO needs concrete controls assigned to an autonomous agent: what kill switches, what escalation thresholds, what audit trails, what documentation, who owns each control: get the ACF® control set scoped to the agent's autonomy level and risk class, with double vocabulary (plain-English recommended_controls + ACF-canonical ddao_controls) for external clarity.

Input parameters:

- `agent_description` (string, required)
- `autonomy_level` (string, required)
- `budget_constraint` (string)
- `locale` (string)
- `risk_level` (string, required)

### `acf.evaluate-agent-mandate` (~123 tokens)

When an existing agent mandate already exists (drafted or proposed for DDAO sign-off) and you need a first-pass audit before go-live or regulatory inspection: does it cover the decision perimeter, the escalation thresholds, the kill switch, the audit trail, the documentation duty?: get a structured preliminary verdict with strengths, gaps, required additions, and explicit gaps_to_validate for the human reviewer.

Input parameters:

- `agent_purpose` (string, required)
- `deployment_context` (string)
- `locale` (string)
- `mandate_text` (string, required)

### `acf.map-to-standards` (~172 tokens)

When a DDAO, an auditor or a compliance officer needs to know which articles of the major external standards (EU AI Act, GDPR, DORA, NIS2, ISO/IEC 42001) each ACF® methodological card connects to: and which ACF® cards a given external article relies on: get the reverse-index built from the same canonical mapping consumed by acf.regulation.article. Useful for cross-mapping audits, regulator filings, and ACF×AI Act conformity arguments. Pass a single fiche_id (e.g. ACF-07) for a focused view, or call without it for the complete inventory of the toolkit cards that the mapping references.

Input parameters:

- `fiche_id` (string)
- `locale` (string)
- `regulations` (array)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/acfstandard-acf-mcp/acf-mcp#diagnostics

## Score history

- 2026-11-05: 59
- 2026-11-04: 58
- 2026-11-03: 58
- 2026-11-02: 57
- 2026-11-01: 57

## Common questions

### What is the io.github.acfstandard/acf-mcp server?

io.github.acfstandard/acf-mcp is listed in the public MCP registry as io.github.acfstandard/acf-mcp. Official ACF® MCP server: Agentic Commerce Framework® governance copilot for AI assistants. This page covers its npm package (acf-mcp).

### Is the io.github.acfstandard/acf-mcp server safe to use?

io.github.acfstandard/acf-mcp scores 59 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.acfstandard/acf-mcp server expose?

io.github.acfstandard/acf-mcp exposes 13 tools: acf.search, acf.fiche.lookup, acf.regulation.article, acf.glossary.define, acf.cite, and 8 more. Their descriptions and schemas cost roughly 1,571 tokens of context every time the server is loaded.

### Is the io.github.acfstandard/acf-mcp server still maintained?

io.github.acfstandard/acf-mcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.acfstandard/acf-mcp server under?

io.github.acfstandard/acf-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/acf-mcp
- Socket report: https://socket.dev/npm/package/acf-mcp
- Website: https://acfstandard.com/
- Changelog RSS feed: https://verifymcp.io/servers/acfstandard-acf-mcp/acf-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/acfstandard-acf-mcp/acf-mcp.json
- HTML version of this page: https://verifymcp.io/servers/acfstandard-acf-mcp/acf-mcp