Searches Google's stock Android documentation knowledge base (~4 800 entries: Jetpack Compose, Camera2, ARCore SDK, Kotlin APIs, platform guides) and returns matching entries with their kb://... URIs. Use this to cross-reference stock Android APIs with SceneView code — e.g. "how does LazyColumn p...
AI agents call search_android_docs to retrieve information from Sceneview without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Free-text search query, e.g. "LazyColumn paging", "Camera2 capture session", "ARCore anchors". |
Parameters from the server's own tool schema.
This is a read-only query tool that retrieves documentation entries from an indexed knowledge base. It has no side effects—it only searches and returns URIs and metadata. The highest severity action is information retrieval with zero blast radius from misuse. The dependency on an optional CLI does not change the nature of the operation, which is purely informational lookup.
From the tool's definition Tool description states it "Searches" and "returns matching entries" from documentation knowledge base. Explicitly designed to "cross-reference" and retrieve information, with follow-up calls to `fetch_android_doc` for reading full entries.
Risk signalsAccepts freeform code/query input (query)
Documented attack patterns abuse exactly the kind of access search_android_docs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sceneview, and nothing reaches the server without passing your rules. This is the rule we recommend for search_android_docs:
{
"version": "1",
"default": "deny",
"tools": {
"search_android_docs": {}
}
}search_android_docs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Searches Google's stock Android documentation knowledge base (~4 800 entries: Jetpack Compose, Camera2, ARCore SDK, Kotlin APIs, platform guides) and returns matching entries with their kb://... URIs. Use this to cross-reference stock Android APIs with SceneView code — e.g. "how does LazyColumn paging work", "Camera2 capture session", "ARCore Config options". Then call fetch_android_doc with a returned URI to read the full entry. Requires Google's android CLI on the MCP host's PATH (an optional runtime dependency — sceneview-mcp works without it); if the CLI is absent the tool returns clear install instructions instead of crashing. It is categorised as a Read tool in the Sceneview MCP Server, which means it retrieves data without modifying state.
search_android_docs accepts 1 parameter: query. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Sceneview MCP server in PolicyLayer and add a rule for search_android_docs: 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.
search_android_docs 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 search_android_docs 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 search_android_docs. 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.
search_android_docs 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.
Start from Sceneview, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Sceneview tools catalogued and risk-classified — across an index of 43,000+ MCP servers.