Track total cost for a 1–20 item basket over 1/3/6/12 months at any rollup scope (national / state / district / chain / urbanisation / region / chain_group). Returns current_total, comparison_total, pct_change, and per-item breakdown. Items missing from either week are listed as missing_items and...
AI agents call basket_watch to retrieve information from ManaMurah MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
basket_watch queries and retrieves consumer price data at various rollup scopes to enable cost tracking and comparison over time periods. This is a read-only operation with no side effects, reversible modifications, code execution, or financial transactions. The tool serves a legitimate analytical purpose for price monitoring and consumer awareness.
From the tool's definition Tool description explicitly states it 'Track[s]' and 'Returns' cost data with comparison metrics (current_total, comparison_total, pct_change, per-item breakdown).
Attacks that exploit this kind of access
Track total cost for a 1–20 item basket over 1/3/6/12 months at any rollup scope (national / state / district / chain / urbanisation / region / chain_group). Returns current_total, comparison_total, pct_change, and per-item breakdown. Items missing from either week are listed as missing_items and excluded from totals (no silent zero-fill). scope=. It is categorised as a Read tool in the ManaMurah MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ManaMurah MCP Server MCP server in PolicyLayer and add a rule for basket_watch: 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 ManaMurah MCP Server. Nothing to install.
basket_watch 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 basket_watch 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 basket_watch. 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.
basket_watch is provided by the ManaMurah MCP Server MCP server (manamurah/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 →