AI agents call object_inspect to retrieve information from Llama without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
object_inspect is a read-only tool that inspects and explains URL or object identifiers. It provides diagnostic information about resources (including handling 404 errors and deleted content lookup) but does not create, modify, delete, or execute any operations.
From the tool's definition Tool description states 'Explain a Llama Command URL or object id' and 'Use for 404s, deleted wiki' — purely informational/diagnostic operations that retrieve or query existing data without modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Explain a Llama Command URL or object id. Use for 404s, deleted wiki. It is categorised as a Read tool in the Llama MCP Server, which means it retrieves data without modifying state.
Register the Llama MCP server in PolicyLayer and add a rule for object_inspect: 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 Llama. Nothing to install.
object_inspect 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 object_inspect 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 object_inspect. 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.
object_inspect is provided by the Llama MCP server (llama-ventures/llama-cli). 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 →