AI agents call agent_bootstrap 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.
This tool retrieves/queries configuration data (a runtime manifest) without side effects. It is a data retrieval operation consistent with Read category. Severity is low as it only exposes runtime configuration information, with minimal blast radius if misused by an agent.
From the tool's definition Tool description states 'Fetch the live Llama Command + Llama OS runtime manifest', which is a retrieval operation with no modification or execution implied.
Attacks that exploit this kind of access
Fetch the live Llama Command + Llama OS runtime manifest. Use this at. 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 agent_bootstrap: 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.
agent_bootstrap 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 agent_bootstrap 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 agent_bootstrap. 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.
agent_bootstrap 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 →