Generate AI context files AND write them directly to the repository. Use with care - this modifies files in the repo. Optionally specify which files to write (default: all).
AI agents use apply_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.
apply_pack creates or modifies files in a repository. This is a reversible write operation (files can be edited or reverted via version control). It is not Destructive because it does not irreversibly delete or overwrite data—modified files can be recovered through Git history. It is not Execute because it doesn't run arbitrary code or shell commands.
From the tool's definition Tool description explicitly states it 'write them directly to the repository' and 'modifies files in the repo'. The warning 'Use with care' reinforces the write capability.
Attacks that exploit this kind of access
Generate AI context files AND write them directly to the repository. Use with care - this modifies files in the repo. Optionally specify which files to write (default: all). 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.
Register the RepoMemory MCP server in PolicyLayer and add a rule for apply_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.
apply_pack is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the apply_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.
Set action: deny in the PolicyLayer policy for apply_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.
apply_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →