get_outcome — Agent Broker MCP Tool Read-only
get_outcome
(get outcome) is one of 23 tools on the
Agent Broker
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call get_outcome from your client
- Claude Code Agent Broker get_outcome run in your project directory
- Claude Desktop Agent Broker get_outcome ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Agent Broker get_outcome ~/.cursor/mcp.json
- VS Code Agent Broker get_outcome .vscode/mcp.json
- Zed Agent Broker get_outcome ~/.config/zed/settings.json
- Windsurf Agent Broker get_outcome ~/.codeium/windsurf/mcp_config.json
- Cline Agent Broker get_outcome ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Agent Broker get_outcome ~/.gemini/settings.json
- Grok Agent Broker get_outcome .mcp.json (in your project root)
- ChatGPT Agent Broker get_outcome Settings → Connectors → Advanced → Developer mode
- Claude.ai Agent Broker get_outcome Settings → Connectors → Add custom connector
- LangChain Agent Broker get_outcome pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agent-broker https://hatchloop.dev/mcp/agent-brokerOther tools on this server
- find_business
- verify_business
- send_message
- capture_lead
- schedule_appointment
- send_transactional_confirmation
- handle_inbound
- escalate_to_human
- get_status
- preview_cost
- self_test
- check_quota
- check_booking_link
- import_booking_url
- call_business
- check_compliance
- verify_company_record
- screen_sanctions
- map_trade_restriction
- get_conversation
- mint_key
- lookup_us_contracts
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.