AgentWork Outcome Router is an MCP server with 10 tools an agent can call, among them buyer_capabilities, get_blocker_resolution, get_opportunity. It answers at https://agent-work-api.agentwork-market.workers.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
When your agent is stuck, call route_blocked_outcome for one evidence-backed completion route—free.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
buyer_capabilities | Inspect AgentWork's disabled-by-default purchasing policy and future Cloudflare Wallet adapter status. |
get_blocker_resolution | 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 Inputs: request_id, request_token, refresh |
get_opportunity | Get one current verified opportunity using the same reusable 24-hour AgentWork pass. Inputs: id |
get_outcome_execution | 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. Inputs: request_id, request_token |
report_blocker_outcome | 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 Inputs: request_id, request_token, outcome, evidence |
request_outcome_execution | 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 o Inputs: task, context, done_when, authority, deadline |
resolve_blocker | 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 Inputs: request, context, authority, max_budget, deadline, preference |
search_services | Search publisher-listed MCP services or x402-discovered paid services with explicit evidence tiers. Inputs: q, source, evidence, network, asset, scheme |
search_work | Search current verified paid work. One x402 settlement grants a reusable 24-hour AgentWork pass. Inputs: source, currency, q, min_amount, max_amount, readiness |
select_blocker_offer | 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 Inputs: request_id, request_token, offer_id, choice |
Every block below points at https://agent-work-api.agentwork-market.workers.dev/mcp. Pick your client and copy.
claude mcp add --transport http agentwork-outcome-router https://agent-work-api.agentwork-market.workers.dev/mcp
{
"mcpServers": {
"agentwork-outcome-router": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://agent-work-api.agentwork-market.workers.dev/mcp"]
}
}
}{
"mcpServers": {
"agentwork-outcome-router": {
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}{
"servers": {
"agentwork-outcome-router": {
"type": "http",
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}{
"context_servers": {
"agentwork-outcome-router": {
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}{
"mcpServers": {
"agentwork-outcome-router": {
"serverUrl": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}{
"mcpServers": {
"agentwork-outcome-router": {
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}name: AgentWork Outcome Router
version: 0.0.1
schema: v1
mcpServers:
- name: AgentWork Outcome Router
type: streamable-http
url: https://agent-work-api.agentwork-market.workers.dev/mcp{
"mcpServers": {
"agentwork-outcome-router": {
"httpUrl": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}{
"mcpServers": {
"agentwork-outcome-router": {
"type": "http",
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}{
"mcpServers": {
"agentwork-outcome-router": {
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fagent-work-api.agentwork-market.workers.dev%2Fmcp&type=streamable_http&id=agentwork-outcome-router&name=AgentWork%20Outcome%20Router
It answered our last check on 22 October 2026 in 270 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
10, as returned by the server's own tools/list on 17 September 2026: buyer_capabilities, get_blocker_resolution, get_opportunity, get_outcome_execution, report_blocker_outcome, request_outcome_execution, resolve_blocker, search_services, and 2 more.
It answered our last check on 22 October 2026 in 270 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agent-work-api.agentwork-market.workers.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.mitchellopzero. Endpoint host: agent-work-api.agentwork-market.workers.dev. ARD identifier: urn:air:io.github.mitchellopzero:mcp:agentwork.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.