store_session_memory · Superkit MCP: Risk & Policy

WHAT IT DOES

What store_session_memory does on Superkit

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

PARAMETERS

Parameter	Type	Required	Description
`tags`	array	—	Optional tags for filtering
`text`	string	Yes	The memory to store (a fact, decision, or pattern)
`ttl_days`	number	—	How long to keep this memory (30 or 90 days)

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why store_session_memory needs a policy

This tool writes/stores data (memories) to a vector store, making it available in future sessions. It is a reversible write operation—data is created and persisted but not inherently destructive. Misuse could pollute the memory store with false or misleading information that influences future AI agent behavior, giving it medium severity.

From the tool's definition Persist a cross-session memory to super-kit's vector store

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

store_session_memory Rate-limited

store_session_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": {
    "store_session_memory": {
      "limits": [
        {
          "counter": "store_session_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 Superkit, so you can run agents against it safely.

FAQ

Questions about store_session_memory

What does the store_session_memory tool do? +

Persist a cross-session memory to super-kit's vector store. Memories are retrieved by semantic similarity in future sessions via recall_memory. It is categorised as a Write tool in the Superkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does store_session_memory accept? +

store_session_memory accepts 3 parameters: tags, text, ttl_days. Required: text. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on store_session_memory? +

Register the Superkit MCP server in PolicyLayer and add a rule for store_session_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 Superkit. Nothing to install.

What risk level is store_session_memory? +

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

Can I rate-limit store_session_memory? +

Yes. Add a rate_limit block to the store_session_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 store_session_memory completely? +

Set action: deny in the PolicyLayer policy for store_session_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 store_session_memory? +

store_session_memory is provided by the Superkit MCP server (superkit-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.