Skip to content

Deploy to Agents

by deploytoagents.com · remote · no sign-in to list tools · v0.3.0 · published by com.deploytoagents

Audit agent-distribution surfaces and create an evidence-based distribution plan.

Changes · 2
CompareRegistry entry

4 tools: 2 change things and 2 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http deploytoagents https://deploytoagents.com/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warncreate_distribution_plan

    The server marks "create_distribution_plan" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_distribution_plan" says "create": a word for a change.

    What this check looks for

Tools

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

4 tools

Changes things 2Claude Code: ask
  • audit_appQueue a bounded audit of a public HTTP or HTTPS app and return an unlisted receipt URL.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.
    Description, as the server wrote it
    Queue a bounded audit of a public HTTP or HTTPS app and return an unlisted receipt URL. Reuse get_audit_result until processing completes.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • create_distribution_planTurn a completed technical audit into prioritized remediation plus official-registry, public-repository, customer-evidence, and independent-discovery actions.1 finding

    Why it is in this group

    • The name "create_distribution_plan" says "create": 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 "create_distribution_plan" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_distribution_plan" says "create": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Turn a completed technical audit into prioritized remediation plus official-registry, public-repository, customer-evidence, and independent-discovery actions.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 2Claude Code: allow
  • get_audit_resultRetrieve the current status, score, findings, privacy state, and evidence URL for an audit UUID.No findings

    Why it is in this group

    • The name "get_audit_result" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve the current status, score, findings, privacy state, and evidence URL for an audit UUID.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_customer_zero_evidenceReturn the public self-audit evidence and the explicit boundary between technical readiness and independent discovery.No findings

    Why it is in this group

    • The name "get_customer_zero_evidence" says "get": a word for reading.
    Description, as the server wrote it
    Return the public self-audit evidence and the explicit boundary between technical readiness and independent discovery.

    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.

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http deploytoagents https://deploytoagents.com/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__deploytoagents__get_audit_result",
      "mcp__deploytoagents__get_customer_zero_evidence"
    ],
    "ask": [
      "mcp__deploytoagents__audit_app",
      "mcp__deploytoagents__create_distribution_plan"
    ],
    "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 deploytoagents. Review it before you use it.