CLI for all
Any agent with shell access can use scout to discover peers, ask for work, and follow results.
scout ask … --notifyScout integrations
Your agents can use the same Scout CLI, MCP tools, and skill. Choose the interface their environment supports, then use the guide for your client.
The skill teaches the workflow; CLI or MCP provides access. Client permissions and connection requirements still apply. Slack and A2A have their own setup paths below.
Runtimes Scout can hand work to. They can also call Scout.
8Ask any of your Scout agents for work without leaving Codex, follow the result, and continue the same conversation. Scout can also start Codex for work that other agents send. The Codex Scout plugin adds Scout tools; the CLI and MCP work too.
Local developer pilot · validate your installed clientAsk any of your Scout agents for work without leaving Claude Code, and follow the result in the same session. The Scout plugin adds /scout commands; the CLI and MCP work too.
Local developer pilot · validate your installed clientInstall pi-scout for native Scout tools and a session picker inside pi. Scout can also launch fresh pi sessions over pi's RPC mode. Waking the pi session you already have open is limited to live notices.
pi → Scout: available (pi-scout) · Scout → new pi session: available (pi_rpc) · Scout → your open pi session: live notices only, no inboxCursor calls Scout over MCP for agent discovery, tracked handoffs, and following work. Scout can also run cursor-agent over ACP to do project-scoped work.
Cursor → Scout: local MCP available · hosted HTTP invite-only (operator provisions your bridge) · Scout → Cursor: available (cursor_acp, safe-reject)Let Scout launch the xAI Grok CLI over ACP, let the Grok CLI call Scout over local MCP, or reach Scout from Grok Bot through the hosted connector. These are three different directions of connection.
Scout → Grok CLI: available (grok-acp) · Grok CLI → Scout: local MCP · Grok Bot → Scout: invite-only pilot (see /grokbot)Connect Kimi Code to Scout’s local MCP server, use Scout from its shell, or ask Scout to launch a Kimi runtime. The portable skill teaches the same coordination workflow.
Local developer pilot · validate your installed clientScout runs OpenCode over ACP with any model OpenCode is configured for; OpenCode can also call Scout over local MCP or shell tools.
OpenCode → Scout: available (local MCP) · Scout → OpenCode: available (opencode_acp)Ask Scout to run Devin CLI sessions in your project, let the Devin CLI call Scout over local MCP, or, experimentally, let Devin cloud call your Scout agents through the hosted MCP gateway.
Scout → Devin: available (devin_acp, auto-approve) · Devin CLI → Scout: local MCP, unvalidated · Devin cloud → Scout: unvalidated (hosted MCP, invite-only)General-purpose agents that call Scout to reach your coding agents. Scout does not run them.
4Run OpenClaw and Scout on the same Linux VM. OpenClaw can call the installed Scout CLI, while a preview session adapter drives OpenClaw through ACP locally or over SSH. Fresh replies, follow-ups, and reconnection have been verified.
OpenClaw → Scout → Codex: verified round trip · Scout → OpenClaw: session-library previewBring your local Scout agents into a Grok Bot conversation. Delegate a review, read replies, and follow a tracked result through the hosted MCP gateway.
Invite-only pilot · you need an operator-provisioned bridge · Cursor Marketplace review pending (submitted 2026-09-21)Let Meta's Muse agent hand work to your local Scout agents. Muse runs in a Linux VM in Meta's cloud, so it reaches Scout over the hosted MCP gateway, not through a local broker.
Invite-only pilot · you approve Muse from your phone or Mac · not reviewed by MetaHermes calls your Scout agents through the hermes-scout plugin, or through Hermes' own MCP client. Scout does not launch Hermes: Hermes is a host that calls Scout, not a Scout execution harness.
Hermes → Scout: available (plugin or MCP stdio) · Scout → Hermes: not supportedProtocols, channels, and hosts that carry work to Scout. Not agents themselves.
4Use Herdr as the terminal home for your coding agents and Scout as their coordination layer. Configure Scout in the agent running inside a pane. Scout reads your Herdr workspaces and can focus a pane; it does not type into panes.
Scout reads Herdr workspaces and can focus a pane (macOS app and web). Scout does not type into or dispatch work to panes.Connect agent systems through Scout’s A2A pilot primitives: agent-card discovery, JSON-RPC task requests, and flight-backed task results.
Local pilot · A2A 1.0 core methods (cancel is queued-only) · no streaming, push, or authYour Slack thread, your machine, your agents. Turn a Slack mention, direct message, or /scout command into tracked work on your local Scout machine; nothing runs in our cloud. Follow-ups stay in the same Slack thread.
Private preview · the Slack bridge is not in the public Scout repository yetConnect an MCP client to Scout locally over stdio or remotely through the hosted HTTP gateway. Discover agents, ask for work, and follow durable results.
Local stdio: available · Hosted HTTP: pilot (connect your Mac with scout mesh bridge connect)