context_prepare_compaction

THE RISK

Medium Risk

Why context_prepare_compaction needs a policy

This tool creates or modifies persisted context data by saving information before a compaction operation. It is reversible (saved context can be overwritten or deleted), so it does not fall into Destructive. It does not execute arbitrary code, move money, or trigger external side effects unpredictably—it performs a storage operation.

From the tool's definition Tool name and description indicate automatic saving of context data: 'Automatically save critical context before compaction'. The verb 'save' combined with 'critical context' suggests creating or persisting data.

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

POLICY

How to control context_prepare_compaction

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "context_prepare_compaction": {
      "limits": [
        {
          "counter": "context_prepare_compaction_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

context_prepare_compaction 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.

Create a free account and register MCP Memory Keeper — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Memory Keeper tools

Destructive context_batch_delete Delete multiple context items by keys or pattern in a single atomic operation Execute context_delegate Delegate complex analysis tasks to specialized agents Execute context_watch Create and manage watchers for real-time context change monitoring Execute context_git_commit Create git commit with automatic context save Write context_session_start Start a new context session with optional project directory for git tracking Write context_cache_file Cache file content with hash for change detection Write context_integrate_tool Track events from other MCP tools Write context_reassign_channel Move context items between channels based on keys, patterns, or entire channel

All 40 MCP Memory Keeper tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about context_prepare_compaction

What does the context_prepare_compaction tool do? +

Automatically save critical context before compaction. It is categorised as a Write tool in the MCP Memory Keeper MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on context_prepare_compaction? +

Register the MCP Memory Keeper MCP server in PolicyLayer and add a rule for context_prepare_compaction: 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 Memory Keeper. Nothing to install.

What risk level is context_prepare_compaction? +

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

Can I rate-limit context_prepare_compaction? +

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

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

context_prepare_compaction is provided by the MCP Memory Keeper MCP server (mkreyman/mcp-memory-keeper). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Memory Keeper tool call.

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

CHECK YOUR STACK →