memory_init_project · Claude Memory MCP: Risk & Policy

WHAT IT DOES

What memory_init_project does on Claude Memory MCP

AI agents use memory_init_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_init_project needs a policy

This tool creates and registers a new database project, which is a reversible modification (the project can be deleted via memory_delete). It does not read/query data (Read), execute arbitrary code (Execute), irreversibly destroy data (Destructive), or handle financial transactions (Financial). The 'creates' action places it in Write category.

From the tool's definition The description states 'creates DuckDB' and 'registers it', which are state-changing operations that create new infrastructure within the system. The tool modifies the persistent memory backend by establishing a new project namespace.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_init_project Rate-limited

memory_init_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_init_project": {
      "limits": [
        {
          "counter": "memory_init_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_init_project

What does the memory_init_project tool do? +

Initialize a new project namespace (creates DuckDB + registers it). 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_init_project? +

Register the Claude Memory MCP server in PolicyLayer and add a rule for memory_init_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_init_project? +

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

Can I rate-limit memory_init_project? +

Yes. Add a rate_limit block to the memory_init_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_init_project completely? +

Set action: deny in the PolicyLayer policy for memory_init_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_init_project? +

memory_init_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.