Skip to content

io.github.CCSTT-dev/callable

by CCSTT-dev · remote · no sign-in to list tools · v1.0.0 · published by GitHub user CCSTT-dev

API for AI agents to delegate tasks to real humans.

Changes · 2
CompareRegistry entry

3 tools: 2 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 callable https://getcallable.dev/api/mcp

Findings

Matches of fixed checks, with the text they matched.

1 info
  • Infosubmit_task

    The input schema at properties.instructions.description mentions "credentials".

    Matched text

    inputSchema.properties.instructions.description: "...rl (where to perform the verification), credentials (login info or how to obtain the code),..."

    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.

3 tools

Changes things 2Claude Code: ask
  • review_taskOptional.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
    Optional. Approve or dispute a task that is in `pending_review` status. Use this after get_task_status reports the operator has completed the work. Approving releases the operator payout. Disputing requires a reason and a description of what is needed for acceptance; the operator is then allowed to resubmit. If you never call review_task, tasks are auto-approved after the review window expires.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • submit_taskSubmit an account verification task to a real human operator.1 finding

    Why it is in this group

    • The name "submit_task" says "submit": a word for a change.

    Findings

    • Info

      The input schema at properties.instructions.description mentions "credentials".

      Matched text

      inputSchema.properties.instructions.description: "...rl (where to perform the verification), credentials (login info or how to obtain the code),..."

      What this check looks for
    Description, as the server wrote it
    Submit an account verification task to a real human operator. Use this when your agent is blocked on something only a real person can complete — a KYC check, a platform sign-in or 2FA prompt, a CAPTCHA, an identity confirmation, or any verification step that requires a human. The task is charged automatically via Stripe ($39). A vetted operator claims it, performs the verification on real hardware, and returns the result (with optional screenshot) to your callback_url or via get_task_status. Typical completion: 30 minutes.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Claude Code: allow
  • get_task_statusPoll the status and retrieve the result of a previously submitted task.No findings

    Why it is in this group

    • The name "get_task_status" says "get": a word for reading.
    Description, as the server wrote it
    Poll the status and retrieve the result of a previously submitted task. Returns the current status (pending, in_progress, pending_review, completed, disputed), the result payload, and any output URLs (video, screenshot). Use this in a polling loop after submit_task if no callback_url was provided.

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

claude mcp add --transport http callable https://getcallable.dev/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__callable__get_task_status"
    ],
    "ask": [
      "mcp__callable__submit_task",
      "mcp__callable__review_task"
    ],
    "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 callable. Review it before you use it.