sources_disable · Claude Role Library MCP: Risk & Policy

WHAT IT DOES

What sources_disable does on Claude Role Library

AI agents use sources_disable to create or update resources in Claude Role Library — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Role Library environment.

WHY IT NEEDS A POLICY

Why sources_disable needs a policy

This tool modifies system state by disabling a prompt source, which is a write operation that changes settings or configuration. It is not destructive because disabling is reversible (the source can be re-enabled), and it does not irreversibly delete data. The medium severity reflects that misconfiguration could impact prompt availability and user experience, but the effect is limited in scope and reversible.

From the tool's definition Tool name 'sources_disable' and description 'Disable a prompt source' indicate modification of configuration state. The action is reversible (sources can be re-enabled), affecting data integrity of the role library system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sources_disable Rate-limited

sources_disable 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": {
    "sources_disable": {
      "limits": [
        {
          "counter": "sources_disable_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 Claude Role Library, so you can run agents against it safely.

FAQ

Questions about sources_disable

What does the sources_disable tool do? +

Disable a prompt source. It is categorised as a Write tool in the Claude Role Library MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sources_disable? +

Register the Claude Role Library MCP server in PolicyLayer and add a rule for sources_disable: 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 Claude Role Library. Nothing to install.

What risk level is sources_disable? +

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

Can I rate-limit sources_disable? +

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

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

sources_disable is provided by the Claude Role Library MCP server (tony427/claude-role-library). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.