Medium Risk

memory_pin

Pin a memory for permanent prioritization (+0.3 boost). USE PROACTIVELY when: user states a persistent constraint, makes an architecture decision, or corrects a misconception. Don

How to control memory_pin ↓

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

Medium Risk

This tool writes/updates data (memory prioritization metadata) reversibly. It does not retrieve (Read), execute arbitrary operations (Execute), permanently delete (Destructive), or involve money (Financial). The 'medium' severity reflects that misuse could skew an agent's recall patterns and decision-making, affecting downstream behavior, but the effect is non-destructive and can be unpinned.

From the tool's definition Tool modifies memory state by applying a '+0.3 boost' to prioritization, which is a reversible metadata update to stored data.

Documented attack patterns abuse exactly the kind of access memory_pin gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and ClawMem, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_pin:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "memory_pin": {
      "limits": [
        {
          "counter": "memory_pin_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

memory_pin 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.

  1. Create a free account and register ClawMem — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the memory_pin tool do? +

Pin a memory for permanent prioritization (+0.3 boost). USE PROACTIVELY when: user states a persistent constraint, makes an architecture decision, or corrects a misconception. Don. It is categorised as a Write tool in the ClawMem 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_pin? +

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

What risk level is memory_pin? +

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

Can I rate-limit memory_pin? +

Yes. Add a rate_limit block to the memory_pin 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_pin completely? +

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

memory_pin is provided by the ClawMem MCP server (yoloshii/clawmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every ClawMem tool call.

Deterministic rules across all 30 ClawMem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

30 ClawMem tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.