Low Risk

get_keyword_recommendations

Get keyword recommendations based on similar keywords and characteristics

How to control get_keyword_recommendations ↓

What get_keyword_recommendations does on Astro MCP Server

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

Low Risk

Why get_keyword_recommendations needs a policy

This tool queries an ASO database to fetch recommendations—a read-only operation with no side effects. It does not create, modify, delete data, execute code, or involve financial transactions. The recommendation engine outputs data analysis based on existing metrics, making it a straightforward Read category tool with low severity risk.

From the tool's definition Tool name is 'get_keyword_recommendations' and description states it retrieves 'keyword recommendations based on similar keywords and characteristics'. This is a retrieval operation with no modification, deletion, code execution, or financial impact.

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

How to control get_keyword_recommendations

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

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

get_keyword_recommendations 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 Astro MCP Server — 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.

Related tools and policies

Go deeper

Questions about get_keyword_recommendations

What does the get_keyword_recommendations tool do? +

Get keyword recommendations based on similar keywords and characteristics. It is categorised as a Read tool in the Astro MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_keyword_recommendations? +

Register the Astro MCP Server MCP server in PolicyLayer and add a rule for get_keyword_recommendations: 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 Astro MCP Server. Nothing to install.

What risk level is get_keyword_recommendations? +

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

Can I rate-limit get_keyword_recommendations? +

Yes. Add a rate_limit block to the get_keyword_recommendations 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 get_keyword_recommendations completely? +

Set action: deny in the PolicyLayer policy for get_keyword_recommendations. 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 get_keyword_recommendations? +

get_keyword_recommendations is provided by the Astro MCP Server MCP server (timbroddin/astro-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Astro MCP Server tool call.

Start from Astro MCP Server, 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.

15 Astro MCP Server tools catalogued and risk-classified — across an index of 43,000+ 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.