search_inventory
AI agents call search_inventory to retrieve information from MCP Maximo Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search tools typically retrieve or query data without modifying state. The absence of create/update/delete verbs in the tool name and its placement alongside other read-only operations (get_*, search_*) indicates this retrieves inventory records.
From the tool's definition Tool name 'search_inventory' and context as sibling to read-only tools like 'get_asset', 'get_inventory', 'get_user_status', 'search_assets', 'search_work_orders' strongly suggest a query/search operation.
Attacks that exploit this kind of access
search_inventory. It is categorised as a Read tool in the MCP Maximo Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Maximo Server MCP server in PolicyLayer and add a rule for search_inventory: 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 MCP Maximo Server. Nothing to install.
search_inventory 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_inventory 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_inventory. 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_inventory is provided by the MCP Maximo Server MCP server (nick0918964388/mcp-maximo-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 →