Low Risk

readonly_query

readonly_query

How to control readonly_query ↓

What readonly_query does on Amazon Bedrock Knowledge Base Retrieval MCP Server

AI agents call readonly_query to retrieve information from Amazon Bedrock Knowledge Base Retrieval 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 readonly_query needs a policy

The tool name strongly suggests a read-only query operation that retrieves data from a knowledge base without side effects. Despite empty description, the 'readonly' prefix provides clear evidence of its non-destructive, non-modifying nature. Severity is low because read-only queries on a knowledge base have minimal blast radius—they cannot alter data, execute arbitrary code, or trigger external operations.

From the tool's definition Tool name 'readonly_query' explicitly contains 'readonly' prefix, indicating read-only semantics without modification capabilities. Server purpose is Bedrock Knowledge Base Retrieval, which is inherently a query/retrieval operation.

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

How to control readonly_query

PolicyLayer is an MCP gateway — it sits between your AI agents and Amazon Bedrock Knowledge Base Retrieval MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for readonly_query:

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

readonly_query 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 Amazon Bedrock Knowledge Base Retrieval 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 readonly_query

What does the readonly_query tool do? +

readonly_query. It is categorised as a Read tool in the Amazon Bedrock Knowledge Base Retrieval MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on readonly_query? +

Register the Amazon Bedrock Knowledge Base Retrieval MCP Server MCP server in PolicyLayer and add a rule for readonly_query: 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 Amazon Bedrock Knowledge Base Retrieval MCP Server. Nothing to install.

What risk level is readonly_query? +

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

Can I rate-limit readonly_query? +

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

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

readonly_query is provided by the Amazon Bedrock Knowledge Base Retrieval MCP Server MCP server (awslabs.bedrock-kb-retrieval-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 Amazon Bedrock Knowledge Base Retrieval MCP Server tool call.

Start from Amazon Bedrock Knowledge Base Retrieval 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.

805 Amazon Bedrock Knowledge Base Retrieval 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.