Skip to content

Agent Conversion

by Ivanpq98 · remote · no sign-in to list tools · v0.1.0 · published by GitHub user Ivanpq98

Run evidence-backed website conversion audits with an AI browsing agent.

Changes · 1
CompareRegistry entry

2 tools: 1 change things and 1 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 agent-conversion https://agent-conversion-coral.vercel.app/api/mcp

Findings

Matches of fixed checks, with the text they matched.

1 info

Tools

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

2 tools

Changes things 1Claude Code: ask
  • test_conversionStart a real Agent Conversion audit: an autonomous browsing agent opens the given website and tries to complete the task, then the run is scored 0-100 with problems and recommendat…1 finding

    Why it is in this group

    • The description's first verb is "start": a word for a change.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...http(s) URL (no localhost, private IPs, credentials or custom ports). task must be 10-1000..."

      What this check looks for
    Description, as the server wrote it
    Start a real Agent Conversion audit: an autonomous browsing agent opens the given website and tries to complete the task, then the run is scored 0-100 with problems and recommendations. Use this when someone wants to know whether an AI agent can find something or complete a commercial step on a specific website, e.g. "Can an agent find the Pro plan's monthly price on example.com?" or "Can an agent start the self-service signup on example.com?". Returns immediately with an audit_id and status "pending" — it does NOT wait for the result. Call get_conversion_report with the audit_id to get the result. Rules: url must be a public http(s) URL (no localhost, private IPs, credentials or custom ports). task must be 10-1000 characters and describe the goal in plain language; phrase purchase-like goals as "reach checkout without buying". Each call costs a real browser run and is rate limited: do not call it repeatedly for the same url+task — poll get_conversion_report instead. Error codes rate_limited, daily_limit and at_capacity mean try again later.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Claude Code: allow
  • get_conversion_reportGet the status and, once finished, the result of an audit started with test_conversion.No findings

    Why it is in this group

    • The name "get_conversion_report" says "get": a word for reading.
    Description, as the server wrote it
    Get the status and, once finished, the result of an audit started with test_conversion. Pass the audit_id returned by test_conversion (a report URL also works). status is "pending" while the agent is still running: wait retry_after_seconds and call again. If stale is true, the audit will never finish; start a new one. When status is "completed", result contains: task_completed (did the agent reach the goal), score (0-100 Agent Conversion Score, or null when score_withheld because the run did not finish measuring), summary, successes, frictions and recommendations; evidence.steps lists what the agent did. failure_classification explains a non-clean run: "blocked" (safety boundary or site-side access refusal such as a bot challenge — a real finding about the site), "run_did_not_finish", "infrastructure_failure" or "pipeline_error" (Agent Conversion's own problem, not the site's). report_url is a human-readable report to share. status "failed" means no report will be produced. Calling this tool is free and safe to repeat.

    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 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-conversion https://agent-conversion-coral.vercel.app/api/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__agent-conversion__get_conversion_report"
    ],
    "ask": [
      "mcp__agent-conversion__test_conversion"
    ],
    "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 agent-conversion. Review it before you use it.