request_outcome — AgentWork Outcomes MCP Tool
request_outcome
(request outcome) is one of 4 tools on the
AgentWork Outcomes
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call request_outcome from your client
- Claude Code AgentWork Outcomes request_outcome run in your project directory
- Claude Desktop AgentWork Outcomes request_outcome ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AgentWork Outcomes request_outcome ~/.cursor/mcp.json
- VS Code AgentWork Outcomes request_outcome .vscode/mcp.json
- Zed AgentWork Outcomes request_outcome ~/.config/zed/settings.json
- Windsurf AgentWork Outcomes request_outcome ~/.codeium/windsurf/mcp_config.json
- Cline AgentWork Outcomes request_outcome ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AgentWork Outcomes request_outcome ~/.gemini/settings.json
- Grok AgentWork Outcomes request_outcome .mcp.json (in your project root)
- ChatGPT AgentWork Outcomes request_outcome Settings → Connectors → Advanced → Developer mode
- Claude.ai AgentWork Outcomes request_outcome Settings → Connectors → Add custom connector
- LangChain AgentWork Outcomes request_outcome pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agentwork-outcomes https://agentwork-outcomes.agentwork-market.workers.dev/mcp?source=mcp-registryOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.