select_repository · RDF4J MCP Server MCP: Risk & Policy

WHAT IT DOES

What select_repository does on RDF4J MCP Server

AI agents use select_repository to create or update resources in RDF4J MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RDF4J MCP Server environment.

WHY IT NEEDS A POLICY

Why select_repository needs a policy

This tool changes application state (the current/default repository) but does not create permanent data objects, delete data, execute arbitrary code, or trigger external operations. It is reversible—another select_repository call can change the default again.

From the tool's definition Tool 'select_repository' modifies state by changing the default repository for subsequent operations. The description states it 'select[s] a repository to use as the default for subsequent operations,' which indicates a state-changing action rather than a…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

select_repository Rate-limited

select_repository stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "select_repository": {
      "limits": [
        {
          "counter": "select_repository_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches RDF4J MCP Server, so you can run agents against it safely.

FAQ

Questions about select_repository

What does the select_repository tool do? +

Select a repository to use as the default for subsequent operations. It is categorised as a Write tool in the RDF4J MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on select_repository? +

Register the RDF4J MCP Server MCP server in PolicyLayer and add a rule for select_repository: 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 RDF4J MCP Server. Nothing to install.

What risk level is select_repository? +

select_repository is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit select_repository? +

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

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

select_repository is provided by the RDF4J MCP Server MCP server (odysa/rdf4j-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.