Radon AI

Use Radon IDE's AI tools for React Native development - query library docs, view logs and network traffic, take screenshots, inspect component trees, and int...

Security Scan

The skill's description promises runtime tools that access app logs, network payloads, screenshots and reloads, but the SKILL.md gives no concrete mechanism, endpoints, or authorization details for how the agent would actually reach those capabilities — that's a mismatch that could hide sensitive-data access or simply be non-functional.

Purpose & Capability

The skill claims to be an MCP server exposing rich runtime tools for Radon IDE (logs, network bodies, screenshots, component tree, reloads). The SKILL.md lists prerequisites (Radon extension, license) but provides no host/URL, port, protocol, RPC schema, or client binding for contacting any MCP server. That gap makes the advertised capabilities incoherent with the provided artifacts — either the skill is incomplete (no connector) or it expects implicit local infrastructure that is not specified. Additionally, the described capabilities inherently grant access to potentially sensitive app data (network bodies, headers, screenshots) which should be explicitly justified and scoped.

Instruction Scope

The runtime instructions direct use of tools that read and return build/runtime logs, full network request details (headers and bodies), and screenshots. These actions can expose secrets (API tokens, PII) from the developer environment or the app under test. The SKILL.md does not specify safeguards, consent flows, filtering, or limits on what data will be returned, nor does it describe how tool calls are made or authorized. It is vague about when and how the agent should call these tools, which grants broad discretion and could lead to over-collection of sensitive data.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing will be downloaded or written by the platform installer. That lowers supply-chain risk compared with skills that fetch binaries or archives.

Credentials

The skill declares no required environment variables or credentials, which is consistent with being an instruction-only descriptor. However, the described tools would access highly sensitive runtime artifacts (network request bodies, headers, logs, screenshots) if the underlying Radon IDE/MCP server is available. Because the SKILL.md does not require or describe any explicit authorization tokens or consent mechanics, it's unclear how access control to those sensitive artifacts is enforced — this mismatch should be clarified before trusting the skill.

Persistence & Privilege

The skill does not request always:true and does not include install-time persistence mechanisms. Autonomous invocation is allowed by default (disable-model-invocation: false), which is platform normal; there is no indication the skill modifies other skills or system-wide settings.

What to consider before installing

This skill claims powerful debugging access (logs, network bodies, screenshots, app control) but the instructions never say how the agent will connect to Radon’s MCP server, what endpoint or auth to use, or what safeguards exist. Before installing or letting the agent use it: (1) Ask the author for the connector details — host/port, API schema, and auth mechanism — and only allow local-only endpoints (e.g., localhost) with explicit consent. (2) Confirm the Radon IDE extension source and license and that it restricts access to test/dev apps (not production data). (3) Request explicit data-handling rules (filtering of secrets, opt-in consent for network bodies/screenshots). (4) Test the skill in an isolated/sandbox environment with no sensitive backends or real credentials. If the author cannot supply concrete connection/auth information and data-protection controls, treat the skill as non-functional or potentially risky and avoid giving it access to sensitive projects.

What this skill provides

Radon AI is an MCP server that provides a set of tools that enhances your agent. It provides up-to-date knowledge of the React Native ecosystem, access to a comprehensive set of debugging data that is otherwise unavailable, and the ability to interact directly with your app.

We index most React Native libraries along with their relevant documentation, versions, APIs, configuration details and usage patterns to provide additional and accurate context. The knowledge database is updated daily.

Available tools

• get_library_description - Returns a detailed description of a library and its use-cases.
• query_documentation - Returns documentation snippets relevant to the provided query.
• reload_application - Triggers a reload of the app running in the development emulator. Use this tool whenever you are debugging the state and want to reset it, or when the app crashes or breaks due to an interaction. There are 3 reload methods:
  • reloadJs: Causes the JS bundle to be reloaded. Does not trigger any rebuild or restart of the native part of the app. Use this to restart the JS state of the app.
  • restartProcess: Restarts the native part of the app. Use this method for resetting state of bugged native libraries or components.
  • rebuild: Rebuilds both the JS and the native parts of the app. Use it whenever changes are made to the native part, as such changes require a full rebuild.
• view_application_logs - Returns all the build, bundling and runtime logs. Use this function whenever the user has any issue with the app, if builds are failing, or when there are errors in the console.
• view_screenshot - Displays a screenshot of the app development viewport. Use this function whenever it is necessary to inspect what the user sees on their mobile device.
• view_component_tree - Displays the component tree (view hierarchy) of the running app. This tool only displays mounted components, so some parts of the project might not be visible. Use this tool when a general overview of the UI is required, such as when resolving layout issues or looking for the relation between the project file structure and component structure.
• view_network_logs - View the contents of the network inspector. Returns a list of all network requests made by the app, including method, URL, status, duration, and size. Use this tool to debug networking issues, inspect API calls, or verify that the app is communicating correctly with backend services. Accepts a pageIndex parameter (0-based index or "latest").
• view_network_request_details - Get all details of a specific network request. Returns headers, body, and other metadata for a given request. Use this tool after view_network_logs to inspect a specific request in detail. Accepts a requestId parameter.

When to use these tools

• When working on a React Native or Expo project that has Radon IDE running in VS Code or Cursor.
• Use query_documentation and get_library_description to look up accurate, current information about libraries instead of relying on training data.
• Use view_application_logs and view_screenshot to debug runtime errors, build failures, or UI issues.
• Use view_component_tree to understand the app's component hierarchy before making structural changes.
• Use reload_application after making code changes to verify fixes or see updates reflected in the running app.
• Use view_network_logs and view_network_request_details to debug networking issues, inspect API calls, or verify backend communication.

Prerequisites

• Radon IDE extension must be installed and active in VS Code or Cursor.
• A React Native or Expo project must be open with Radon IDE running.
• An active Radon IDE license.

Limitations

• Responses augmented by Radon AI are still prone to LLM errors. Verify important information before acting on it!
• The knowledge base contains documentation files only - it does not index the full source code of the libraries.