Low Risk

memory_pack

Build a formatted memory pack from search results — quick one-shot context block.

How to control memory_pack ↓

What memory_pack does on Codemem

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

Low Risk

Why memory_pack needs a policy

The tool reads and formats existing memory/search results into a context block. It retrieves and organizes data without creating, modifying, or deleting anything. The phrase 'from search results' confirms it is a read/query operation with no side effects.

From the tool's definition Build a formatted memory pack from search results — quick one-shot context block

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

How to control memory_pack

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

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

memory_pack 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 Codemem — 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.

Related tools and policies

Go deeper

Questions about memory_pack

What does the memory_pack tool do? +

Build a formatted memory pack from search results — quick one-shot context block. It is categorised as a Read tool in the Codemem MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on memory_pack? +

Register the Codemem MCP server in PolicyLayer and add a rule for memory_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 Codemem. Nothing to install.

What risk level is memory_pack? +

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

Can I rate-limit memory_pack? +

Yes. Add a rate_limit block to the memory_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 memory_pack completely? +

Set action: deny in the PolicyLayer policy for memory_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 memory_pack? +

memory_pack is provided by the Codemem MCP server (kunickiaj/codemem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Codemem tool call.

Start from Codemem, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

13 Codemem tools catalogued and risk-classified — across an index of 43,000+ 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.