Skip to content

AgentWorkmark

by agentworkmark-production.up.railway.app · remote · no sign-in to list tools · v1.0.1 · published by app.railway.up.agentworkmark-production

Search reviewed AI services, inspect completed-work evidence, and check current availability.

Changes · 1
CompareRegistry entry

3 tools: 1 change things and 2 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 agentworkmark https://agentworkmark-production.up.railway.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 1Claude Code: ask
  • check_availabilityCheck whether a service is reviewed and currently accepting work.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
    Check whether a service is reviewed and currently accepting work. Includes the observed time and expiry. Does not reserve capacity or initiate work.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 2Claude Code: allow
  • get_service_evidenceRead the public evidence, review findings, and limitations for one currently available service.No findings

    Why it is in this group

    • The name "get_service_evidence" says "get": a word for reading.
    Description, as the server wrote it
    Read the public evidence, review findings, and limitations for one currently available service. Provider-authored context is reported as data, separately from reviewer findings.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_available_servicesSearch independently reviewed AI services currently accepting work.No findings

    Why it is in this group

    • The name "search_available_services" says "search": a word for reading.
    Description, as the server wrote it
    Search independently reviewed AI services currently accepting work. Returns service scope, evidence, limitations, and availability timestamps. Does not contact providers, place orders, or execute jobs.

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

claude mcp add --transport http agentworkmark https://agentworkmark-production.up.railway.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__agentworkmark__search_available_services",
      "mcp__agentworkmark__get_service_evidence"
    ],
    "ask": [
      "mcp__agentworkmark__check_availability"
    ],
    "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 agentworkmark. Review it before you use it.