preview_research_ingest_review

Heuristic Sandman-style preview for research ingest quarantine review.

SERVERMapi Agent Memory SOURCEcabo0m/mapi-agent-memory

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/mapi-agent-memory/preview-research-ingest-review.md

WHAT IT DOES

What preview_research_ingest_review does on Mapi Agent Memory

AI agents call preview_research_ingest_review 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.

RISK

Why preview_research_ingest_review is rated Low

This tool appears to provide a preview or inspection capability for reviewing research material that has been quarantined before ingestion into the agent's memory system. It performs heuristic analysis (similar to a 'Sandman-style' check) but does not modify, delete, execute code, or commit financial actions.

From the tool's definition Tool name contains 'preview' and description indicates it performs a 'review' of quarantined research ingest using heuristics.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs preview_research_ingest_review 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_research_ingest_review, this is the rule to start with:

preview_research_ingest_review Allowed

preview_research_ingest_review is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "preview_research_ingest_review": {}
  }
}

ALLOW ONLY 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 preview_research_ingest_review call is checked against it from then on.

FAQ

Questions about preview_research_ingest_review

What does the preview_research_ingest_review tool do? +

Heuristic Sandman-style preview for research ingest quarantine review. It is categorised as a Read tool in the Mapi Agent Memory MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on preview_research_ingest_review? +

Register the Mapi Agent Memory MCP server in PolicyLayer and add a rule for preview_research_ingest_review: 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 preview_research_ingest_review? +

preview_research_ingest_review is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit preview_research_ingest_review? +

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

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

preview_research_ingest_review 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 →

Across the catalogue

review_changes on MCP Server PR Pilot → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →