Other · Remote MCP server
AgentWork Outcome Router
When your agent is stuck, call route_blocked_outcome for one evidence-backed completion route—free.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.mitchellOpZero/agentwork- Version
- 0.1.2
- Status
- Active
- Category
- other
- Transport
- Streamable HTTP
- Published
- 2026-08-14
- Updated
- 2026-08-14
- Publisher
- mitchellOpZero (GitHub) · 2 servers with pages here
- Website
- agentwork-api.mitchellmosesai.chatgpt.site/
- Repository
- github.com/mitchellOpZero/agentwork
- Source
- Registry API entry
Remote endpoints
| Transport | URL | Headers declared |
|---|---|---|
| Streamable HTTP | https://agent-work-api.agentwork-market.workers.dev/mcp | None |
How to connect AgentWork Outcome Router
AgentWork Outcome Router is a remote MCP server: there is nothing to install. Its endpoint is https://agent-work-api.agentwork-market.workers.dev/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.
No headers are declared in the registry entry. If the server needs you to sign in, a client that supports MCP authorization opens the service's own sign-in page when it first connects.
Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
Site checks
The website's own root, agentwork-api.mitchellmosesai.chatgpt.site, was checked for the files that tell AI systems about a site.
| File | Result |
|---|---|
/llms.txt | Real file, HTTP 200 · 2026-10-04 |
/.well-known/mcp.json | No real file found |
/.well-known/ai-plugin.json | No real file found |
/agents.json | No real file found |
More from mitchellOpZero (GitHub)
| Server | Runs |
|---|---|
| AgentWork OutcomesBuy a finished outcome through services, agents, marketplaces, humans, tools, or swarms. | Remote · HTTP |
More other servers
| Server | Runs |
|---|---|
| AgenttrustTrust scores & reputation for the agent-to-agent economy. Verify A2A counterparties. | Local · stdio |
| AgentTrust — Pre-Invocation AI Agent Trust & Reliability ChecksCheck an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision. | Remote · HTTP |
| AgentVaultDiscover, verify, and connect to AI agents with E2E encrypted messaging and trust scoring. | Local · stdio |
| AgentwatchCheck if ChatGPT, Claude and Perplexity can reach, read and quote a website. | Remote · HTTP |
| AgentWorld DiscoveryRead-only AgentWorld discovery: join instructions, activities, public stats, and Reason Lab. | Remote · HTTP |
| AgentWorld DiscoveryRead-only discovery for AgentWorld WORLD, A2A onboarding and the separate MARKET service economy. | Remote · HTTP |
| AgentyThe link page for AI agents — discover agents and read their handles across platforms. | Remote · HTTP |