project_memory · Booster MCP: Risk & Policy

WHAT IT DOES

What project_memory does on Booster MCP

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

WHY IT NEEDS A POLICY

Why project_memory needs a policy

The tool description translates to 'Management of long-term project memory,' implying it can read, write, or update persistent memory/notes about a project. 'Management' typically implies CRUD operations. Since it can create or modify stored data (project memory), Write is the most appropriate category. However, confidence is moderate because the description is vague and does not specify exact operations.

From the tool's definition "Управление долгосрочной памятью проекта" (Management of long-term project memory)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

project_memory Rate-limited

project_memory 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": {
    "project_memory": {
      "limits": [
        {
          "counter": "project_memory_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 Booster MCP, so you can run agents against it safely.

FAQ

Questions about project_memory

What does the project_memory tool do? +

Управление долгосрочной памятью проекта. It is categorised as a Write tool in the Booster 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 project_memory? +

Register the Booster MCP server in PolicyLayer and add a rule for project_memory: 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 Booster MCP. Nothing to install.

What risk level is project_memory? +

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

Can I rate-limit project_memory? +

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

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

project_memory is provided by the Booster MCP server (neuroghostdev/booster_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.