run_sandman_ai

Sandman AI (wykonanie) Ă˘â‚¬â€ť uÄąÄ˝ywa LM Studio (Qwen) do oceny wspomnieÄąâ€ž i wprowadza zmiany.

SERVERMapi Agent Memory SOURCEcabo0m/mapi-agent-memory

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/mapi-agent-memory/run-sandman-ai.md

WHAT IT DOES

What run_sandman_ai does on Mapi Agent Memory

AI agents invoke run_sandman_ai to trigger actions in Mapi Agent Memory. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why run_sandman_ai is rated High

This tool executes an external LM (Qwen via LM Studio) to perform evaluations and apply modifications to AI agent memory. While the description is somewhat unclear due to encoding/language issues, the core function is executing an AI model with side effects (introducing changes to memory).

From the tool's definition Tool description indicates 'wykonanie' (execution in Polish) and that it 'uses LM Studio (Qwen) to assess memories and introduces changes.' The phrase 'introduces changes' combined with the execute-oriented framing suggests the tool runs an AI model to modify…

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_sandman_ai safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mapi Agent Memory, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_sandman_ai, this is the rule to start with:

run_sandman_ai Rate-limited

run_sandman_ai stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_sandman_ai": {
      "limits": [
        {
          "counter": "run_sandman_ai_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mapi Agent Memory, apply this rule, and every run_sandman_ai call is checked against it from then on.

FAQ

Questions about run_sandman_ai

What does the run_sandman_ai tool do? +

Sandman AI (wykonanie) Ă˘â‚¬â€ť uÄąÄ˝ywa LM Studio (Qwen) do oceny wspomnieÄąâ€ž i wprowadza zmiany. It is categorised as a Execute tool in the Mapi Agent Memory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_sandman_ai? +

Register the Mapi Agent Memory MCP server in PolicyLayer and add a rule for run_sandman_ai: 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 Mapi Agent Memory. Nothing to install.

What risk level is run_sandman_ai? +

run_sandman_ai is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_sandman_ai? +

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

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

run_sandman_ai is provided by the Mapi Agent Memory MCP server (cabo0m/mapi-agent-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mapi Agent Memory, and thousands of servers like it.

This server

All 252 Mapi Agent Memory tools → High-risk tools on this server →

Across the catalogue

run on 0sec →shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →