preview_sandman_ai
Sandman AI (preview) — używa LM Studio (Qwen) do oceny wspomnień.
This record as markdown: /tools/mapi-agent-memory/preview-sandman-ai.md
What preview_sandman_ai does on Mapi Agent Memory
AI agents call preview_sandman_ai to retrieve information from Mapi Agent Memory without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why preview_sandman_ai is rated Low
This tool appears to analyze or evaluate agent memories using a language model for assessment purposes. The description is partially in Polish and somewhat garbled, making interpretation difficult, which reduces confidence slightly. However, the core functionality appears to be querying and analyzing existing memory data without modifying it, making it a Read operation.
From the tool's definition Tool name 'preview_sandman_ai' with description indicating it performs evaluation/assessment ('do oceny') of memories using an LM Studio model. The word 'preview' suggests a non-production read operation.
Attacks that exploit this kind of access
The rule that runs preview_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 preview_sandman_ai, this is the rule to start with:
preview_sandman_ai is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mapi Agent Memory, apply this rule, and every preview_sandman_ai call is checked against it from then on.
Questions about preview_sandman_ai
Sandman AI (preview) — używa LM Studio (Qwen) do oceny wspomnień. It is categorised as a Read tool in the Mapi Agent Memory MCP Server, which means it retrieves data without modifying state.
Register the Mapi Agent Memory MCP server in PolicyLayer and add a rule for preview_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.
preview_sandman_ai is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the preview_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.
Set action: deny in the PolicyLayer policy for preview_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.
preview_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.
More on Mapi Agent Memory, and thousands of servers like it.
This server
Across the catalogue