Which integrations are available for this server?

Integrates with MobX-State-Tree to view state changes and actions, allowing AI assistants to debug state management flows. Provides debugging capabilities for React and React Native apps, including reading logs, inspecting app state, monitoring network requests, and triggering custom commands. Enables viewing Redux action history and dispatching actions to the app for state management analysis.

How do I use reactotron-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@reactotron-mcp Show me the recent error logs" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

reactotron-mcp

by steve228uk

Overview Schema Related Servers Score Discussions

TypeScript

Local

reactotron-mcp

Install in VS Code Install in Cursor

An MCP (Model Context Protocol) server for Reactotron, enabling AI assistants to read logs, inspect app state, monitor network requests, and trigger custom commands in your React or React Native app.

How it works

The MCP server runs a WebSocket proxy between your app and the Reactotron desktop app:

App ──► MCP Proxy (port 9091) ──► Reactotron (port 9090)
               │
          captures everything
               │
          MCP tools (Claude/Cursor etc.)

Your app connects to the proxy instead of directly to Reactotron. The proxy forwards all traffic to Reactotron (so the desktop UI works normally) and captures every message for the MCP tools.

The proxy works in standalone mode — if Reactotron is not open, the app connection is kept alive and all messages are still captured. When Reactotron is opened later, the proxy reconnects automatically (with exponential backoff). This means you don't need to have Reactotron running before starting your app.

Related MCP server: Curupira

Requirements

Your app pointed at the proxy port (default 9091) instead of Reactotron directly
Reactotron desktop app (optional — for the visual UI)

Installation

Claude Code

claude mcp add reactotron-mcp npx reactotron-mcp

Or with Bun:

claude mcp add reactotron-mcp bunx reactotron-mcp

npx (Node)

{
  "mcpServers": {
    "reactotron": {
      "command": "npx",
      "args": ["-y", "reactotron-mcp"]
    }
  }
}

bunx (Bun)

{
  "mcpServers": {
    "reactotron": {
      "command": "bunx",
      "args": ["reactotron-mcp"]
    }
  }
}

Custom port

If Reactotron is running on a non-default port, set REACTOTRON_PORT:

{
  "mcpServers": {
    "reactotron": {
      "command": "npx",
      "args": ["-y", "reactotron-mcp"],
      "env": {
        "REACTOTRON_PORT": "9090"
      }
    }
  }
}

App setup

Point your app's Reactotron config at the proxy port instead of the default:

// Before
Reactotron.configure({ host: 'localhost' }).connect()

// After
Reactotron.configure({ host: 'localhost', port: 9091 }).connect()

Configuration

Environment variable	Default	Description
`REACTOTRON_PROXY_PORT`	`9091`	Port the MCP proxy listens on (apps connect here)
`REACTOTRON_PORT`	`9090`	Port the Reactotron desktop app is running on
`REACTOTRON_TIMEOUT`	`5000`	Timeout in ms for state queries

Tools

Tool	Description
`get_logs`	Read captured log messages. Filter by level (`log`/`debug`/`warn`/`error`), text search, and limit.
`get_state`	Query the app's state tree. Browse keys at a path or read the value.
`get_network`	View captured API requests and responses. Filter by URL, HTTP method, status code, minimum duration, and limit.
`get_timeline`	Full chronological timeline of all Reactotron messages.
`get_state_actions`	View completed Redux or MobX-State-Tree actions. Filter by action type substring and limit.
`get_state_changes`	View state mutation events. Filter by state path substring and limit.
`get_benchmarks`	View performance benchmark reports with per-step timings. Filter by title and limit.
`get_displays`	Read custom display messages sent via `reactotron.display()`. Filter by name/preview text and limit.
`get_errors`	Consolidated view of error-level logs and failed network requests (4xx/5xx) in one call.
`get_images`	Retrieve images logged via `reactotron.image()`, rendered inline as native MCP image content.
`get_app_info`	Show connected app metadata from the Reactotron handshake: name, version, platform, React/RN versions.
`get_connection_status`	Check whether an app is connected, including app name, platform, and proxy port.
`run_custom_command`	List or trigger custom commands registered by the app.
`dispatch_action`	Dispatch a Redux or MobX-State-Tree action to the app.
`clear_messages`	Clear captured messages from the in-memory buffer. Clears all buffers or a specific message type.
`list_custom_commands`	List all custom commands currently registered by the connected app.

Resources

Resources expose the same data as tools but as readable URIs, useful for attaching live context directly to a conversation.

Resource	URI	Description
Logs	`reactotron://logs`	Latest 50 log messages
Network	`reactotron://network`	Latest 50 network requests
Timeline	`reactotron://timeline`	Latest 100 messages across all types
State	`reactotron://state{/path*}`	App state at a given path (e.g. `reactotron://state/user/profile`)
State Actions	`reactotron://state-actions`	Latest 50 Redux/MST actions
State Changes	`reactotron://state-changes`	Latest 50 state mutations
Benchmarks	`reactotron://benchmarks`	Latest 50 benchmark reports
Display Messages	`reactotron://displays`	Latest 50 `reactotron.display()` messages
Custom Commands	`reactotron://custom-commands`	All registered custom commands
Connection	`reactotron://connection`	Connection status and app info
Images	`reactotron://images`	Metadata list of captured images (use `get_images` tool to view inline)

Prompts

Prompts are reusable templates that guide the AI through common debugging workflows. Invoke them via your AI assistant's prompt/slash-command interface.

Prompt	Description
`debug_app`	Get a comprehensive debug snapshot — checks connection, logs, network, state, and recent actions.
`trace_action`	Trace a specific Redux/MST action through its payload, state changes, logs, and network side effects. Takes an `action` argument (e.g. `AUTH/LOGIN_SUCCESS`).
`diagnose_network`	Identify and analyse failed or errored API requests, spot patterns, and check related state.
`debug_performance`	Analyse benchmark reports and slow network requests to identify performance bottlenecks.
`debug_errors`	Triage all errors — error logs, failed requests, important display messages, and error state.

Development

bun install
bun run dev       # run from source
bun run build     # bundle for distribution
bun run typecheck # type-check without building

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

0dRelease cycle

2Releases (12mo)

Commit activity

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/steve228uk/reactotron-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server