// SCAN REPORT

Reactotron

16 tools. 2 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

2 can modify or destroy data

14 read-only

16 tools total

Community server · catalogue entry verified 29/06/2026

How to control Reactotron ↓

TOOL MAP

What Reactotron exposes to your agents

Read (14) Write / Execute (1) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Reactotron tools

Destructive · High clear_messages Clear captured Reactotron messages from the in-memory buffer. Clears all buffers by default, or a specific message type. Execute · Medium run_custom_command Trigger a custom command registered by the app in Reactotron. Call with no

2 of Reactotron's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Reactotron

PolicyLayer is an MCP gateway — it sits between your AI agents and Reactotron, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clear_messages": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations

{
  "dispatch_action": {
    "limits": [
      {
        "counter": "dispatch_action_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Reactotron — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON REACTOTRON →

Instant setup, no code required.

FULL CATALOGUE

All 16 Reactotron tools

DESTRUCTIVE 1 tools

Destructive clear_messages Clear captured Reactotron messages from the in-memory buffer. Clears all buffers by default, or a specific mes

EXECUTE 1 tools

Execute run_custom_command Trigger a custom command registered by the app in Reactotron. Call with no

READ 14 tools

Read dispatch_action Dispatch a Redux or MobX-State-Tree action to the app via Reactotron. Read get_app_info Retrieve metadata about the connected app as reported in its Reactotron client.intro handshake — app name, ver Read get_benchmarks Retrieve performance benchmark reports captured from the connected app via Reactotron. Read get_connection_status Check whether a React/React Native app is currently connected to the Reactotron proxy, including app metadata. Read get_displays Retrieve custom display messages sent via reactotron.display(). These are structured debug entries with a name Read get_errors Get a consolidated view of all errors: error-level logs and failed network requests (4xx/5xx). Useful for a qu Read get_images Retrieve images logged via reactotron.image(). Returns each image rendered inline alongside its metadata (file Read get_logs Retrieve log messages captured from the connected React/React Native app via Reactotron. Read get_network Retrieve captured API/network requests and responses from the app. Read get_state Query the app Read get_state_actions Retrieve completed Redux or MobX-State-Tree actions captured from the connected app via Reactotron. Read get_state_changes Retrieve state mutation events captured from the connected app via Reactotron. Read get_timeline Retrieve the full timeline of recent Reactotron messages across all types (logs, network, state actions, custo Read list_custom_commands List all custom commands currently registered by the connected app in Reactotron.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Reactotron

Can an AI agent delete data through the Reactotron MCP server? +

Yes. The Reactotron server exposes 1 destructive tools including clear_messages. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the Reactotron MCP server expose? +

16 tools across 3 categories: Destructive, Execute, Read. 14 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Reactotron? +

Register the Reactotron MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Reactotron tool call.

Deterministic rules across all 16 Reactotron tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON REACTOTRON →

Instant setup, no code required.

16 Reactotron tools catalogued and risk-classified — across an index of 43,000+ MCP servers.