AI agents call get_discard_summary to retrieve information from Sana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'get_discard_summary' strongly suggests it retrieves summary information without modifying state. This aligns with sibling Read operations like 'search_discard_history', 'lookup_trip_details', and 'get_discard_reasons'. No evidence of destructive, financial, or execution capabilities. The empty description lowers confidence slightly, but the semantic pattern is clear.
From the tool's definition Tool name 'get_discard_summary' suggests retrieving or querying summary data about discarded items. The empty description limits certainty, but the pattern of sibling tools (search_*, lookup_*, get_*, evaluate_*) on this inventory/packing server indicates…
Attacks that exploit this kind of access
get_discard_summary. It is categorised as a Read tool in the Sana MCP Server, which means it retrieves data without modifying state.
Register the Sana MCP server in PolicyLayer and add a rule for get_discard_summary: 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 Sana. Nothing to install.
get_discard_summary 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 get_discard_summary 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 get_discard_summary. 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.
get_discard_summary is provided by the Sana MCP server (sana-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →