AI agents use pitch_finalize to commit financial operations through Llama — usually the final step of a payment, billing, or trading workflow. A call moves real money.
pitch_finalize moves real money, and an autonomous agent will call it with the same confidence it calls a search tool. A misread instruction or an injected prompt is all it takes to drain an account or blow a budget.
Attacks that exploit this kind of access
Clear the local pitch session state. Note: this does not force the. It is categorised as a Financial tool in the Llama MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Llama MCP server in PolicyLayer and add a rule for pitch_finalize: 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.
pitch_finalize is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the pitch_finalize 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 pitch_finalize. 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.
pitch_finalize 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 →