Medium Risk

cursor_code_assist

Log Cursor AI code assistance interactions with auto-memory

How to control cursor_code_assist ↓

What cursor_code_assist does on SAM

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

Medium Risk

Why cursor_code_assist needs a policy

The tool logs/records code assistance interactions and saves them to memory (auto-memory), which is a write/create operation storing data persistently. It creates new memory entries rather than retrieving existing ones. The 'auto-memory' aspect indicates data is being written to a memory store. Severity is medium as it could inadvertently capture and persist sensitive code or context.

From the tool's definition Log Cursor AI code assistance interactions with auto-memory

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

How to control cursor_code_assist

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

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

cursor_code_assist 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 SAM — 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.

Related tools and policies

Go deeper

Questions about cursor_code_assist

What does the cursor_code_assist tool do? +

Log Cursor AI code assistance interactions with auto-memory. It is categorised as a Write tool in the SAM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on cursor_code_assist? +

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

What risk level is cursor_code_assist? +

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

Can I rate-limit cursor_code_assist? +

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

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

cursor_code_assist is provided by the SAM MCP server (pigrieco/mcp-memory-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SAM tool call.

Start from SAM, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

37 SAM tools catalogued and risk-classified — across an index of 43,000+ 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.