Low Risk

pack_codebase

Package a local code directory into a consolidated file for AI analysis. This tool analyzes the codebase structure, extracts relevant code content, and generates a comprehensive report including metrics, file tree, and formatted code content. Supports multiple output formats: XML (structured with...

How to control pack_codebase ↓

AI agents call pack_codebase to retrieve information from Repomix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

pack_codebase retrieves and processes existing codebase data to generate reports and packaged output. It has no side effects on the underlying repository or file system — it only reads code content and reformats it. The tool explicitly does not execute code, delete files, or modify the repository. This is fundamentally a Read operation with organizational/formatting enhancements.

From the tool's definition Tool description states it 'analyzes the codebase structure, extracts relevant code content, and generates a comprehensive report' — core functions are analysis and reading.

Documented attack patterns abuse exactly the kind of access pack_codebase gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Repomix, and nothing reaches the server without passing your rules. This is the rule we recommend for pack_codebase:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "pack_codebase": {}
  }
}

pack_codebase is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Repomix — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the pack_codebase tool do? +

Package a local code directory into a consolidated file for AI analysis. This tool analyzes the codebase structure, extracts relevant code content, and generates a comprehensive report including metrics, file tree, and formatted code content. Supports multiple output formats: XML (structured with <file> tags), Markdown (human-readable with ## headers and code blocks), JSON (machine-readable with files as key-value pairs), and Plain text (simple format with separators). Also supports Tree-sitter compression for efficient token usage. It is categorised as a Read tool in the Repomix MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on pack_codebase? +

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

What risk level is pack_codebase? +

pack_codebase is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit pack_codebase? +

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

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

pack_codebase is provided by the Repomix MCP server (yamadashy/repomix). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Repomix tool call.

Deterministic rules across all 8 Repomix tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

8 Repomix tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.