AI agents call search_discard_history 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 'search' prefix and 'history' suffix suggest this tool queries or retrieves past discard records without modifying data. Despite the empty description lowering confidence slightly, the consistent naming convention with other Read-category tools and absence of any modification or deletion semantics supports Read classification. No side effects or irreversible actions are implied.
From the tool's definition Tool name 'search_discard_history' indicates retrieval/querying of historical discard data. No description provided, but the naming pattern aligns with other Read operations on the server (search_item_inventory, search_items, search_trips,…
Attacks that exploit this kind of access
search_discard_history. 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 search_discard_history: 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.
search_discard_history 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 search_discard_history 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 search_discard_history. 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.
search_discard_history 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 →