add_to_scoped_memory · consciousness MCP server MCP

WHAT IT DOES

What add_to_scoped_memory does on consciousness MCP server

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

WHY IT NEEDS A POLICY

Why add_to_scoped_memory needs a policy

This tool creates or modifies data in a scoped (session-limited) vector memory store. It is reversible—scoped memory is temporary and can be cleared via sibling tools like clear_scoped_memory or forget_scoped_memory. The blast radius is low because the changes are session-scoped, not persistent, and semantically limited to memory embeddings. It does not execute code, delete irreversibly, or move money.

From the tool's definition Tool name is 'add_to_scoped_memory' and description states 'Store information in session-scoped vector memory'. The verb 'Store' and the 'add_to' prefix indicate data creation/modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_to_scoped_memory Rate-limited

add_to_scoped_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": {
    "add_to_scoped_memory": {
      "limits": [
        {
          "counter": "add_to_scoped_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 consciousness MCP server, so you can run agents against it safely.

FAQ

Questions about add_to_scoped_memory

What does the add_to_scoped_memory tool do? +

Store information in session-scoped vector memory. It is categorised as a Write tool in the consciousness MCP server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_to_scoped_memory? +

Register the consciousness MCP server MCP server in PolicyLayer and add a rule for add_to_scoped_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 consciousness MCP server. Nothing to install.

What risk level is add_to_scoped_memory? +

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

Can I rate-limit add_to_scoped_memory? +

Yes. Add a rate_limit block to the add_to_scoped_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 add_to_scoped_memory completely? +

Set action: deny in the PolicyLayer policy for add_to_scoped_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 add_to_scoped_memory? +

add_to_scoped_memory is provided by the consciousness MCP server MCP server (one710/consciousness). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.