AI agents use brief_add_callout to create or update resources in Llama — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Llama environment.
The tool adds content to a brief rather than executing arbitrary code or deleting data. While it modifies a deal brief (potentially important business context), the operation is reversible and limited in scope. Medium severity reflects that misuse could inject misleading information into deal briefs, but the blast radius is contained to brief content modifications rather than system-wide or financial impact.
From the tool's definition Tool description states 'Prepend a callout block to a deal brief', which creates or modifies data by adding a block to an existing brief.
Attacks that exploit this kind of access
Prepend a callout block to a deal brief. Use for emphasized insights or warnings. It is categorised as a Write tool in the Llama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Llama MCP server in PolicyLayer and add a rule for brief_add_callout: 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.
brief_add_callout is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the brief_add_callout 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 brief_add_callout. 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.
brief_add_callout 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 →