// SCAN REPORT

Sana

11 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 5 Jul 2026

1 can modify or destroy data

10 read-only

11 tools total

Community server · catalogue entry verified 05/07/2026

How to control Sana ↓

TOOL MAP

What Sana exposes to your agents

Read (10) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Sana tools

Write · Medium update_item The tool name 'update_item' directly indicates a write operation that modifies existing data.

1 of Sana's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sana

PolicyLayer is an MCP gateway — it sits between your AI agents and Sana, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "update_item": {
    "limits": [
      {
        "counter": "update_item_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "evaluate_item_data_quality": {
    "limits": [
      {
        "counter": "evaluate_item_data_quality_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Sana — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SANA →

Instant setup, no code required.

FULL CATALOGUE

All 11 Sana tools

WRITE 1 tools

Write update_item update_item

READ 10 tools

Read evaluate_item_data_quality evaluate_item_data_quality Read evaluate_trip_packing_readiness evaluate_trip_packing_readiness Read find_expired_inventory find_expired_inventory Read get_discard_reasons get_discard_reasons Read get_discard_summary get_discard_summary Read lookup_trip_details lookup_trip_details Read search_discard_history search_discard_history Read search_item_inventory search_item_inventory Read search_items search_items Read search_trips search_trips

FAQ

Questions about Sana

How do I prevent bulk modifications through Sana? +

The Sana server has 1 write tools including update_item. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Sana.

How many tools does the Sana MCP server expose? +

11 tools across 2 categories: Read, Write. 10 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Sana? +

Register the Sana MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Sana tool call.

Deterministic rules across all 11 Sana tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SANA →

Instant setup, no code required.

11 Sana tools catalogued and risk-classified — across an index of 43,000+ MCP servers.