Skip to content

AgentWork Outcome Router

by mitchellOpZero · remote · no sign-in to list tools · v0.1.2 · published by GitHub user mitchellOpZero

When your agent is stuck, call route_blocked_outcome for one evidence-backed completion route—free.

Changes · 4
CompareRegistry entry

10 tools: 4 change things and 6 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 agentwork https://agent-work-api.agentwork-market.workers.dev/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.

10 tools

Changes things 4Claude Code: ask
  • report_blocker_outcomeReport what happened after following the selected route.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
    Report what happened after following the selected route. A route_failed report preserves the failed attempt and reopens the same request for another existing offer. Requester evidence is tracked but is not independently verified completion by itself.
  • request_outcome_executionHand AgentWork an outcome your agent cannot execute.No findings

    Why it is in this group

    • The name "request_outcome_execution" says "request": a word for a change.
    Description, as the server wrote it
    Hand AgentWork an outcome your agent cannot execute. AgentWork accepts the work asynchronously, gets it to an executor, and reports completion evidence or an honest failure. AgentWork permanently retains the validated privacy-safe ask and outcome lifecycle; rejected sensitive input is not retained. This is not provider search. Save the private token from the initial call to read status.
  • resolve_blockerSubmit one real task your agent cannot finish.1 finding

    Why it is in this group

    • The name "resolve_blocker" says "resolve": a word for reading.
    • The description's first verb is "submit": a word for a change.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...Call get_blocker_resolution with those credentials to run or read privacy-safe discovery a..."

      What this check looks for
    Description, as the server wrote it
    Submit one real task your agent cannot finish. AgentWork immediately returns a private request ID and token before running supply discovery. Call get_blocker_resolution with those credentials to run or read privacy-safe discovery and obtain a current complete route or an honest no_credible_route. Save the token: it is returned only once. Discovery cannot invoke, procure, pay, post, or expose private context.
  • select_blocker_offerSelect one persisted blocker offer on the original request.No findings

    Why it is in this group

    • The name "select_blocker_offer" says "select": a word for a change.
    Description, as the server wrote it
    Select one persisted blocker offer on the original request. Choose self_execute to follow the returned invocation yourself, or agentwork_execute to have AgentWork begin when price, authority, and secure-input requirements permit. Selection does not silently charge or procure anything.
Only reads 6Claude Code: allow
  • buyer_capabilitiesInspect AgentWork's disabled-by-default purchasing policy and future Cloudflare Wallet adapter status.No findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.
    Description, as the server wrote it
    Inspect AgentWork's disabled-by-default purchasing policy and future Cloudflare Wallet adapter status.
  • get_blocker_resolutionRead the private persisted route or owner-confirmed escalation lifecycle on the same AgentWork request ID.No findings

    Why it is in this group

    • The name "get_blocker_resolution" says "get": a word for reading.
    Description, as the server wrote it
    Read the private persisted route or owner-confirmed escalation lifecycle on the same AgentWork request ID. Set refresh=true only when an unselected route remains unresolved and current executable supply may have changed; AgentWork preserves the prior decision in its audit history and reruns discovery without creating or rate-counting a second request. Refresh is cooldown- and attempt-limited. This tool cannot confirm for an owner. Put the request token in this tool argument, never a URL.
  • get_opportunityGet one current verified opportunity using the same reusable 24-hour AgentWork pass.No findings

    Why it is in this group

    • The name "get_opportunity" says "get": a word for reading.
    Description, as the server wrote it
    Get one current verified opportunity using the same reusable 24-hour AgentWork pass.
  • get_outcome_executionRead the private execution status and completion evidence.No findings

    Why it is in this group

    • The name "get_outcome_execution" says "get": a word for reading.
    Description, as the server wrote it
    Read the private execution status and completion evidence. Put the token in this tool argument, never a URL. Poll only while the status is received or accepted.
  • search_servicesSearch publisher-listed MCP services or x402-discovered paid services with explicit evidence tiers.No findings

    Why it is in this group

    • The name "search_services" says "search": a word for reading.
    Description, as the server wrote it
    Search publisher-listed MCP services or x402-discovered paid services with explicit evidence tiers.
  • search_workSearch current verified paid work.No findings

    Why it is in this group

    • The name "search_work" says "search": a word for reading.
    Description, as the server wrote it
    Search current verified paid work. One x402 settlement grants a reusable 24-hour AgentWork pass.

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

claude mcp add --transport http agentwork https://agent-work-api.agentwork-market.workers.dev/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__agentwork__get_blocker_resolution",
      "mcp__agentwork__get_outcome_execution",
      "mcp__agentwork__search_work",
      "mcp__agentwork__get_opportunity",
      "mcp__agentwork__search_services",
      "mcp__agentwork__buyer_capabilities"
    ],
    "ask": [
      "mcp__agentwork__resolve_blocker",
      "mcp__agentwork__select_blocker_offer",
      "mcp__agentwork__report_blocker_outcome",
      "mcp__agentwork__request_outcome_execution"
    ],
    "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 agentwork. Review it before you use it.