Low Risk

search_skills

Full-text search the android/skills library by keyword or natural-language query. Returns ranked matches with a short snippet. Call this BEFORE answering any non-trivial Android question — the curated skills carry the canonical Google guidance and will outrank your training data. Then call get_sk...

How to control search_skills ↓

AI agents call search_skills to retrieve information from Android Skills MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

search_skills is a read-only query operation that searches a library and returns information. It has no capacity to modify, delete, or execute external operations. The blast radius of misuse is minimal: worst case, an AI agent performs inefficient searches or receives irrelevant results. No data integrity, system state, or external systems are at risk.

From the tool's definition Tool performs 'full-text search' and 'returns ranked matches with a short snippet' — pure retrieval with no side effects, creation, modification, or deletion of data.

Documented attack patterns abuse exactly the kind of access search_skills gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Android Skills MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_skills:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_skills": {}
  }
}

search_skills is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Android Skills MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the search_skills tool do? +

Full-text search the android/skills library by keyword or natural-language query. Returns ranked matches with a short snippet. Call this BEFORE answering any non-trivial Android question — the curated skills carry the canonical Google guidance and will outrank your training data. Then call get_skill with the top result to read its full content. It is categorised as a Read tool in the Android Skills MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_skills? +

Register the Android Skills MCP server in PolicyLayer and add a rule for search_skills: 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 Android Skills MCP. Nothing to install.

What risk level is search_skills? +

search_skills is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_skills? +

Yes. Add a rate_limit block to the search_skills 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.

How do I block search_skills completely? +

Set action: deny in the PolicyLayer policy for search_skills. 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.

What MCP server provides search_skills? +

search_skills is provided by the Android Skills MCP server (skydoves/android-skills-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Android Skills MCP tool call.

Deterministic rules across all 3 Android Skills MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

3 Android Skills MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.