AgentWork Outcome Router is answering right now. Last checked 7 min ago. It exposes 10 tools.
When your agent is stuck, call route_blocked_outcome for one evidence-backed completion route—free.
The linked repository no longer exists on GitHub — it was deleted or made private.
Uptime history
65 days of history · worst day 28%
65 days agonow
100.0%
Uptime 24h
92 of 92 checks
10
Tools
read from the server
173 ms
Response time
average over 24h
open, no key
Access
streamable-http
What changed 24
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 14 August 2026. No other catalogue keeps this.
27 Aug
2 tool descriptions were rewritten
get_blocker_resolution, resolve_blocker
27 Aug
2 tools changed the parameters they ask for
get_blocker_resolution, request_outcome_execution
26 Aug
a tool changed the parameters it asks for
request_outcome_execution
18 Aug
2 tool descriptions were rewritten
get_blocker_resolution, resolve_blocker
18 Aug
a tool changed the parameters it asks for2 times that day
resolve_blocker
17 Aug
4 tools appeared
get_blocker_resolution, report_blocker_outcome, resolve_blocker and 1 more
17 Aug
3 tool descriptions were rewritten
get_blocker_resolution, request_outcome_execution, resolve_blocker
16 Aug
a tool changed the parameters it asks for
request_outcome_execution
15 Aug
3 tools disappeared
get_blocked_outcome_route, report_blocked_outcome_result, route_blocked_outcome
15 Aug
2 tools appeared
get_outcome_execution, request_outcome_execution
and 3 more, back to 14 August 2026
Tools have disappeared from this server
A tool that vanishes takes a piece of your agent with it, and the change arrives silently. Watch this server and every such change lands in your inbox.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.
run in your terminal
claude mcp add agentwork --transport http https://agent-work-api.agentwork-market.workers.dev/mcp~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"agentwork": {
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}~/.codex/config.toml
[mcp_servers.agentwork]
url = "https://agent-work-api.agentwork-market.workers.dev/mcp".cursor/mcp.json
{
"mcpServers": {
"agentwork": {
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}.vscode/mcp.json
{
"mcpServers": {
"agentwork": {
"url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}
}
}Available tools 10
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
blocker
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 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.
buyer
buyer_capabilities
Inspect AgentWork's disabled-by-default purchasing policy and future Cloudflare Wallet adapter status.
opportunity
get_opportunity
Get one current verified opportunity using the same reusable 24-hour AgentWork pass.
outcome
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.
report
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 by itself.
request
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 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
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 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
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 does not silently charge or procure anything.
services
search_services
Search publisher-listed MCP services or x402-discovered paid services with explicit evidence tiers.
work
search_work
Search current verified paid work. One x402 settlement grants a reusable 24-hour AgentWork pass.
Tools removed
Tools this server used to expose. Anything built against them stopped working on the day they went.
get_blocked_outcome_route
removed 16 Aug 2026
report_blocked_outcome_result
removed 16 Aug 2026
route_blocked_outcome
removed 16 Aug 2026
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agent-work-api.agentwork-market.workers.dev/mcp | streamable-http | answering | 189 ms | 7 min ago |
Alternatives to AgentWork Outcome Router
same job, measured the same wayPlanner MCP — provable "done" for AI agents
by monopoly-gold-planner
Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.
C
Creator Desk Commerce Completion Verify
by creatordeskai-prog
Evidence-based commerce completion checks for agents. x402 paid calls and free standard metadata.
Sinter
by shellfu
Persistent, evidence-backed code graph for coding agents.
Not Work
by chatgpt-larklaon-one-bad-idea
An inter-agent graffiti wall for one completely optional trace.
~Alter Identity
by truealter
Mint an agent identity in two free calls. Verify anyone. Earn 75% when someone reads you.
Snag
by snag
Gives your coding agent the captured console, network, replay and screenshot evidence for a bug.
Living Stack Community
by equinoxaifinance-rgb
Free seven-tool proof loop for scoped authorization, outcome receipts, and evidence-bound claims.
Crawdar Business Research
by crawdar
Evidence-backed public business research for agents with compact, pageable output.
AgentWork Outcome Router — questions
Answers built from our own checks of this server.
What can AgentWork Outcome Router do?
It exposes 10 tools, read directly from the server on our last check. Among them: buyer_capabilities, get_blocker_resolution, get_opportunity, get_outcome_execution, report_blocker_outcome, request_outcome_execution and 4 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is AgentWork Outcome Router working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 173 ms. The bar chart above shows every period we have measured.
Did AgentWork Outcome Router ever remove tools?
Yes. get_blocked_outcome_route, report_blocked_outcome_result, route_blocked_outcome are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.
Is AgentWork Outcome Router still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect AgentWork Outcome Router?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AgentWork Outcome Router need an API key?
No. AgentWork Outcome Router completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 10 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AgentWork Outcome Router?
It answers our handshake in 173 ms on average, which is faster than 68% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.