search_packages
AI agents call search_packages to retrieve information from Mirelia-Structured-Data-Marketplace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the name 'search_packages' strongly suggests querying/listing patent data packages without modification. Even in a marketplace context with financial sibling tools (purchase_single_patent, verify_crypto_payment_and_deliver), search functionality is a Read operation.
From the tool's definition Tool name 'search_packages' indicates a search operation. The description is empty, limiting direct evidence, but search operations are canonically Read-category (retrieve or query data).
Attacks that exploit this kind of access
search_packages. It is categorised as a Read tool in the Mirelia-Structured-Data-Marketplace MCP Server, which means it retrieves data without modifying state.
Register the Mirelia-Structured-Data-Marketplace MCP server in PolicyLayer and add a rule for search_packages: 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 Mirelia-Structured-Data-Marketplace. Nothing to install.
search_packages 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_packages 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_packages. 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_packages is provided by the Mirelia-Structured-Data-Marketplace MCP server (stagproject/mirelia-structured-data-marketplace). 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 →