sources_add · Claude Role Library MCP: Risk & Policy

WHAT IT DOES

What sources_add does on Claude Role Library

AI agents use sources_add 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_add needs a policy

This tool creates a new prompt source reference, which is a reversible data modification. It does not delete data (Destructive), execute arbitrary commands (Execute), move money (Financial), or merely read data (Read).

From the tool's definition The tool name 'sources_add' and description 'Add a new prompt source (e.g., GitHub repository)' indicate a create/add operation that modifies the sources configuration by introducing a new entry.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sources_add Rate-limited

sources_add 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_add": {
      "limits": [
        {
          "counter": "sources_add_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_add

What does the sources_add tool do? +

Add a new prompt source (e.g., GitHub repository). 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_add? +

Register the Claude Role Library MCP server in PolicyLayer and add a rule for sources_add: 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_add? +

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

Can I rate-limit sources_add? +

Yes. Add a rate_limit block to the sources_add 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_add completely? +

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

sources_add 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.