generate_pack · RepoMemory MCP: Risk & Policy

WHAT IT DOES

What generate_pack does on RepoMemory

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

WHY IT NEEDS A POLICY

Why generate_pack needs a policy

This tool creates or modifies repository configuration and metadata files (CLAUDE.md, .claudeignore, hooks). These changes are reversible—files can be edited, deleted, or regenerated. The impact is confined to repository configuration rather than production data.

From the tool's definition Tool description states it will 'Generate AI context files' including CLAUDE.md, .claudeignore, slash commands, and pre-commit hooks. The verb 'generate' and the list of file artifacts indicate creation of new files or configuration modifications.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_pack Rate-limited

generate_pack 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": {
    "generate_pack": {
      "limits": [
        {
          "counter": "generate_pack_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 RepoMemory, so you can run agents against it safely.

FAQ

Questions about generate_pack

What does the generate_pack tool do? +

Generate AI context files (CLAUDE.md, .claudeignore, slash commands, pre-commit hook) for a repository. Requires AI_PROVIDER_API_KEY to be set. Uses the configured AI model to generate repo-specific content. It is categorised as a Write tool in the RepoMemory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_pack? +

Register the RepoMemory MCP server in PolicyLayer and add a rule for generate_pack: 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 RepoMemory. Nothing to install.

What risk level is generate_pack? +

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

Can I rate-limit generate_pack? +

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

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

generate_pack is provided by the RepoMemory MCP server (praveenjayaprakash-jp/repomemory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.