Coordinate local coding agents and track handoffs. For high-trust developer pilots.
Quick Install
Automated & IDE SetupCopy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.
Manual Client & Custom JSON ConfigExpand JSON â–¾
No confirmed setup config for this listing yet. We only publish a config block when the install details come from the project itself — its README, its docs, or a verified owner. We haven’t found those for OpenScout, and we’d rather show nothing than a guess you’d paste into your client. Follow the project’s own setup instructions for the current steps.
Documentation Overview
Scout — coordinate Claude Code, Codex, and other AI agents
Your personal agent cloud.
A local control plane and mesh network for coding agents across the machines you own.
Scout connects coding agents through a local broker for agent-to-agent communication, multi-agent coding workflows, and tracked code reviews. Ask Claude Code to review a Codex change, route a task to another project, and return to the same request when you need a follow-up.
Keep using your existing agent tools and provider accounts. Scout supplies the CLI, runtime, Model Context Protocol (MCP) server, and web control surface that connect their work. Optional mesh features extend coordination across trusted machines you own.
Current posture: Scout is for high-trust local developer pilots. It is not yet a hardened multi-tenant or compliance-ready control plane.
Quickstart · Workflows · Integrations · MCP setup · Common questions · Architecture · Documentation
What can you do with Scout?
| Your task | A practical workflow |
|---|---|
| Get a second code review | Implement with Codex, then ask Claude Code to inspect a stable diff and return findings. Keep the review read-only until you assess the result. |
| Run coding agents in parallel | Give workers separate tasks and worktrees, track their requests, and keep one owner responsible for integration. Worktrees do not isolate shared databases or ports. |
| Hand off between projects | Include the destination project, goal, constraints, and expected result in the request. The receiving session needs that context explicitly. |
| Follow up without losing the thread | Save the returned reference, read the result, and ask a follow-up against the same work. An accepted request is distinct from completed work. |
| Coordinate across trusted machines | Use the mesh and pairing workflow to extend reachability. Check the destination checkout and runtime; reachability does not synchronize files or agent transcripts. |
Start with Claude Code and Codex code review, then explore multi-agent coding and AI agent orchestration.
Get started
Local coordination uses Bun 1.3 or newer and at least one installed, authenticated coding-agent tool. Start on Apple Silicon macOS:
Installing the package does not start services silently. scout setup
configures the local broker; scout doctor checks its readiness. On Linux, run
the broker as a foreground process under your process manager; follow the
quickstart for that lifecycle.
Have Claude Code review a Codex change
From the project containing the change, pause edits while the reviewer reads it. Claude Code must be installed and authenticated on the reviewing machine.
Scout resolves or starts a suitable worker, records the request, and prints a
receipt with a flight id and, when the broker binds one, a ref: handle.
--notify returns after that receipt instead of holding your terminal. Replace
ref:RETURNED below with the handle from your receipt:
scout wait also accepts the flight or invocation id. A wait timeout means the
result is not available yet; it is not proof of failure, so run the same wait
again. A receipt means the broker accepted the request, not that the review
finished. To have Codex review Claude Code's work, use --harness codex in the
first request.
Choose your agent tool
A harness runs the coding agent. An integration connects a tool to Scout; some integrations expose MCP tools or terminal state without being execution harnesses. Use the setup link for the tool you already work in.
| Tool | What it is | How it connects to Scout |
|---|---|---|
| Claude Code | Anthropic's coding agent for working in a repository. | Route review or implementation tasks with --harness claude; the Claude Code plugin adds Scout commands and channel integration. |
| OpenAI Codex | OpenAI's coding-agent tooling, including a CLI. | Route tasks with --harness codex; the Codex plugin supplies MCP tools and coordination guidance. |
| Cursor | An AI code editor with agent tooling. | The Cursor integration connects the editor to scout mcp. Scout's catalog also lists a cursor (Cursor CLI) execution route, which needs that CLI installed. |
| Grok CLI | xAI's terminal coding agent (Grok Build), binary grok. | Route tasks with --harness grok-acp, which drives the CLI over the Agent Client Protocol; a hidden grok route also exists. Grok Bot, xAI's hosted agent product, can call Scout through a separate hosted MCP connector, currently an operator-assisted pilot; it is not a launchable worker. |
| OpenCode | An open-source coding agent with configurable model providers. | Route tasks with --harness opencode. Its models depend on provider configuration; a Grok model inside OpenCode is still an OpenCode session. See the OpenCode guide. |
| Kimi Code | Kimi's terminal coding agent. | Route tasks with --harness kimi; see the Kimi guide for setup. |
| Devin | Coding-agent tooling with its own execution environment. | Scout's catalog includes a Devin route. Follow the Devin integration guide for its prerequisites and current limits; catalog presence alone does not establish account access. |
| pi | An extensible terminal coding-agent tool. | The pi extension brings Scout messages, requests, and agent discovery into pi sessions; Scout also lists a pi execution route. |
| Hermes Agent | An agent host with its own sessions and tools. | The Hermes plugin bridges Scout MCP tools into those sessions. Hermes is an MCP host, not a Scout dispatch harness. |
| Herdr | A terminal host for working with agent panes. | Herdr exposes terminal and agent-state surfaces around supported sessions. It is not a model or dispatch harness. |
| Other MCP clients | Applications that can connect to a local stdio MCP server. | Configure scout mcp using the MCP setup below. Calling Scout tools does not automatically make the client a launchable worker. |
Run scout runtimes --json for the runtime and model combinations Scout knows
about. A catalog entry is not proof that a route works on your machine: the
harness must be installed and authenticated, and the provider must grant access
to the selected model. scout doctor reports local readiness. See the integration catalog
for additional tool-specific guides and their current setup requirements.
Collaboration across Claude Code, Codex, Grok, and OpenCode
Scout connects coding agents as collaborating peers. No tool has a fixed role or authority over another. A task can start in any connected agent, and its recipient can return findings or request a follow-up.
Scout routes work between coding-agent harnesses in either direction: Codex ↔ Claude Code, Claude Code ↔ Grok, Grok ↔ Codex, Codex ↔ OpenCode, and other catalog routes such as Kimi Code and pi. A direction works when two things are true:
- the destination harness is installed and authenticated where it runs;
- the calling session can reach Scout, by running the
scoutCLI or through Scout's MCP tools.
Change --harness to claude, codex, opencode, or kimi to pick a
different destination. Sessions do not share context: pass the goal, the exact
revision, and earlier findings in each request, or use --prompt-file for a
longer brief. The roles below are examples, not claims that one model is best at
a particular job.
Related MCP Servers
Reviews
No reviews yet — be the first to share how this listing worked for you.
Frequently Asked Questions about OpenScout
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/openscout)HTML Embed
<a href="https://allmcps.com/mcp/openscout"><img src="https://allmcps.com/api/badge/openscout?style=directory" alt="OpenScout on AllMCPs" /></a>