Low Risk

search_classes

Search for Java classes in internal company libraries found in the local Maven/Gradle caches. Essential for finding classes in internal company libraries that are not part of the current workspace source code. Use this when you see an import (e.g.,

How to control search_classes ↓

What search_classes does on Maven Indexer

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

Low Risk

Why search_classes needs a policy

The tool performs read-only search operations against indexed Maven/Gradle caches to retrieve class information and signatures. It does not execute code, modify data, delete resources, or trigger external operations. The scope is limited to querying cached library metadata, making it a low-risk Read operation.

From the tool's definition search_classes: 'Search for Java classes in internal company libraries found in the local Maven/Gradle caches.' This is a search/query operation that retrieves class metadata from local caches with no modification, deletion, or execution of code.

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

How to control search_classes

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

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

search_classes 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 Maven Indexer — 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 search_classes

What does the search_classes tool do? +

Search for Java classes in internal company libraries found in the local Maven/Gradle caches. Essential for finding classes in internal company libraries that are not part of the current workspace source code. Use this when you see an import (e.g.,. It is categorised as a Read tool in the Maven Indexer MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_classes? +

Register the Maven Indexer MCP server in PolicyLayer and add a rule for search_classes: 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 Maven Indexer. Nothing to install.

What risk level is search_classes? +

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

Can I rate-limit search_classes? +

Yes. Add a rate_limit block to the search_classes 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_classes completely? +

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

search_classes is provided by the Maven Indexer MCP server (tangcent/maven-indexer-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Maven Indexer tool call.

Start from Maven Indexer, 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.

6 Maven Indexer 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.