save_code_run

THE RISK

Medium Risk

Why save_code_run needs a policy

This tool writes/stores data about code executions and their results. While it creates persistent records, it is reversible (data can be updated or removed separately via other tools like delete_memory), making it Write rather than Destructive.

From the tool's definition Tool name 'save_code_run' and description 'Save successful code runs and their outputs' indicate creation/persistence of data (code execution records and outputs) without deletion or financial impact.

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

POLICY

How to control save_code_run

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 save_code_run:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_code_run": {
      "limits": [
        {
          "counter": "save_code_run_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

save_code_run 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.

Create a free account and register SAM — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More SAM tools

Destructive delete_memory Delete a memory Execute trigger_auto_analysis Manually trigger automatic analysis of conversation Write cascade_interaction Log interaction with Windsurf Cascade AI Write cursor_code_assist Log Cursor AI code assistance interactions with auto-memory Write log_collaboration Log collaboration activities in a Repl Write auto_save_memory Automatically save memory if content triggers the threshold Write configure_triggers Configure automatic trigger settings Write cursor_project_context Update project context and learning patterns

All 37 SAM tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about save_code_run

What does the save_code_run tool do? +

Save successful code runs and their outputs. 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 save_code_run? +

Register the SAM MCP server in PolicyLayer and add a rule for save_code_run: 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 save_code_run? +

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

Can I rate-limit save_code_run? +

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

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

save_code_run 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.

CHECK YOUR STACK →