add_labels · Mcp Github Pm MCP: Risk & Policy

WHAT IT DOES

What add_labels does on Mcp Github Pm

AI agents use add_labels to create or update resources in Mcp Github Pm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Github Pm environment.

WHY IT NEEDS A POLICY

Why add_labels needs a policy

This tool modifies issue state by attaching labels, which is a non-destructive write operation. Labels can be easily removed, making this a standard metadata update. The blast radius is minimal since label changes do not affect core issue data, financial systems, or enable code execution. Severity is 'low' because misuse would result in cosmetic/organizational issues rather than data loss or system compromise.

From the tool's definition Tool name 'add_labels' and description 'Add labels to an existing issue' indicate modification of issue metadata. Labels are reversible attributes that can be added or removed without data loss or destructive consequences.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_labels Rate-limited

add_labels 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": {
    "add_labels": {
      "limits": [
        {
          "counter": "add_labels_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 Mcp Github Pm, so you can run agents against it safely.

FAQ

Questions about add_labels

What does the add_labels tool do? +

Add labels to an existing issue. It is categorised as a Write tool in the Mcp Github Pm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_labels? +

Register the Mcp Github Pm MCP server in PolicyLayer and add a rule for add_labels: 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 Mcp Github Pm. Nothing to install.

What risk level is add_labels? +

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

Can I rate-limit add_labels? +

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

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

add_labels is provided by the Mcp Github Pm MCP server (lordbasilaiassistant-sudo/mcp-github-pm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.