memory_attach_project · Claude Memory MCP: Risk & Policy

WHAT IT DOES

What memory_attach_project does on Claude Memory MCP

AI agents use memory_attach_project to create or update resources in Claude Memory MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Memory MCP environment.

WHY IT NEEDS A POLICY

Why memory_attach_project needs a policy

This tool modifies application state by attaching and activating a project, which is a write-class operation (reversible via detach). It affects which project's memory is currently accessible but does not create permanent data structures beyond the attachment record itself, nor does it execute arbitrary code. The 'Auto-activates' phrase indicates side effects but within the scope of project state management.

From the tool's definition Attaches (connects/registers) an existing project directory to the memory system and auto-activates it. This is a state-modifying operation that changes the active project context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_attach_project Rate-limited

memory_attach_project 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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Memory MCP, so you can run agents against it safely.

FAQ

Questions about memory_attach_project

What does the memory_attach_project tool do? +

Attach an existing project directory. Auto-activates on success. It is categorised as a Write tool in the Claude Memory MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on memory_attach_project? +

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

What risk level is memory_attach_project? +

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

Can I rate-limit memory_attach_project? +

Yes. Add a rate_limit block to the memory_attach_project 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_attach_project completely? +

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

memory_attach_project is provided by the Claude Memory MCP server (navid-kianfar/claude-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.