Scans a local SceneView project on the user's machine and returns a structured analysis: detected project type (Android, iOS, Web), extracted SceneView dependency version, whether it is outdated vs the latest known release, and any known anti-patterns found by reading source files (threading viol...
Risk signalsAccepts file system path (path)
Part of the Sceneview server.
Free to start. No card required.
AI agents call analyze_project to retrieve information from Sceneview without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though analyze_project only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"analyze_project": {}
}
}See the full Sceneview policy for all 28 tools.
These attack patterns abuse exactly the kind of access analyze_project gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Scans a local SceneView project on the user's machine and returns a structured analysis: detected project type (Android, iOS, Web), extracted SceneView dependency version, whether it is outdated vs the latest known release, and any known anti-patterns found by reading source files (threading violations, LightNode trailing-lambda bug, deprecated 2.x APIs, Sceneform imports). Safe: scans at most 30 source files and 500 KB total, never writes to disk. Use this when a user asks 'is my project up to date?', 'what's wrong with my SceneView code?', or when you want a fast sanity check of a project before generating code for it.. It is categorised as a Read tool in the Sceneview MCP Server, which means it retrieves data without modifying state.
Register the Sceneview MCP server in PolicyLayer and add a rule for analyze_project: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sceneview. Nothing to install.
analyze_project is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the analyze_project rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for analyze_project. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
analyze_project is provided by the Sceneview MCP server (SceneView/sceneview). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 28 Sceneview tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.