Skip to content

AgencyAI Commerce MCP

by barnaby-coder · remote · no sign-in to list tools · v1.1.0 · published by GitHub user barnaby-coder

AgencyAI's public MCP for service discovery and AI-readiness assessment.

Changes · 2
CompareRegistry entry

3 tools: 2 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agencyai https://agencyai-mcp.vercel.app/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 2Claude Code: ask
  • assess_ai_readinessProduce a deterministic, indicative AI-readiness assessment from the supplied organization profile.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
    Produce a deterministic, indicative AI-readiness assessment from the supplied organization profile.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • book_consultationSubmit a consultation request preview.No findings

    Why it is in this group

    • The description's first verb is "submit": a word for a change.
    Description, as the server wrote it
    Submit a consultation request preview. This legacy flow does not send email, create calendar events, or guarantee a booking.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: false
Only reads 1Claude Code: allow
  • get_service_offeringsRead AgencyAI's current AI operations service catalog and return packages matching a client profile.No findings

    Why it is in this group

    • The name "get_service_offerings" says "get": a word for reading.
    Description, as the server wrote it
    Read AgencyAI's current AI operations service catalog and return packages matching a client profile.

    Annotations the server declares

    • readOnlyHint: 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.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agencyai https://agencyai-mcp.vercel.app/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agencyai__get_service_offerings"
    ],
    "ask": [
      "mcp__agencyai__assess_ai_readiness",
      "mcp__agencyai__book_consultation"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agencyai. Review it before you use it.