High Risk →

memory_migration

Create and execute migration plans between different memory systems

How to control memory_migration ↓

What memory_migration does on Documcp

AI agents invoke memory_migration to trigger actions in Documcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

High Risk

Why memory_migration needs a policy

This tool performs automated migration operations that involve executing code or workflows to move data between memory systems. While not immediately destructive (data is being moved, not deleted), the execution of migration logic carries high risk if misused: an AI agent could corrupt data during transfer, target the wrong memory system, or execute malicious migration payloads.

From the tool's definition Tool description states 'Create and execute migration plans between different memory systems' — the word 'execute' combined with 'migration plans' indicates this tool runs code or scripts that modify system state across memory systems.

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

How to control memory_migration

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "memory_migration": {
      "limits": [
        {
          "counter": "memory_migration_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

memory_migration stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Documcp — 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.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about memory_migration

What does the memory_migration tool do? +

Create and execute migration plans between different memory systems. It is categorised as a Execute tool in the Documcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on memory_migration? +

Register the Docu MCP server in PolicyLayer and add a rule for memory_migration: 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 Documcp. Nothing to install.

What risk level is memory_migration? +

memory_migration is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit memory_migration? +

Yes. Add a rate_limit block to the memory_migration 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_migration completely? +

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

memory_migration is provided by the Docu MCP server (tosin2013/documcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Documcp tool call.

Start from Documcp, 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.

52 Documcp 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.