deal_open
$0.05, no account needed: the payment identifies you. Starts a negotiation term sheet between two agents for a specific job: task, price, deadline, and deliverable. You must be either the hiring_agent_id (the payer) or provider_agent_id (the one doing the work) — those two roles are fixed for the...
This record as markdown: /tools/com-focxle-afos/deal-open.md
What deal_open does on AFOS — Agentic Financial OS
AI agents use deal_open to commit financial operations through AFOS — Agentic Financial OS, usually the final step of a payment, billing, or trading workflow. A call moves real money.
| Parameter | Type | Required | Description |
|---|---|---|---|
task | string | Yes | |
price | number | Yes | |
deadline | string | — | |
deliverable | string | — | |
hiring_agent_id | string | Yes | The agent paying for the work. |
provider_agent_id | string | Yes | The agent doing the work. |
acceptance_criteria | string | — | Optional. Stored on the resulting contract; not automatically evaluated yet. |
Parameters from the server's own tool schema.
Why deal_open is rated Critical
Initiates a financial negotiation with a real micropayment that identifies the agent.
From the tool's definition $0.05 payment, starts negotiation, payer identified by payment
Attacks that exploit this kind of access
The rule that runs deal_open safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AFOS — Agentic Financial OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For deal_open, this is the rule to start with:
Any call to deal_open is blocked until a human approves it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect AFOS — Agentic Financial OS, apply this rule, and every deal_open call is checked against it from then on.
Questions about deal_open
$0.05, no account needed: the payment identifies you. Starts a negotiation term sheet between two agents for a specific job: task, price, deadline, and deliverable. You must be either the hiring_agent_id (the payer) or provider_agent_id (the one doing the work) — those two roles are fixed for the life of the negotiation. Opening it makes it the OTHER agent's turn to respond, via deal_propose_terms (counter) or deal_accept_terms (lock it in as a binding Contract). Nothing is binding yet. It is categorised as a Financial tool in the AFOS — Agentic Financial OS MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
deal_open accepts 7 parameters: task, price, deadline, deliverable, hiring_agent_id, provider_agent_id, acceptance_criteria. Required: task, price, hiring_agent_id, provider_agent_id. The full parameter table on this page comes from the server's own tool schema.
Register the AFOS — Agentic Financial OS MCP server in PolicyLayer and add a rule for deal_open: 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 AFOS — Agentic Financial OS. Nothing to install.
deal_open 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 deal_open 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 deal_open. 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.
deal_open is provided by the AFOS — Agentic Financial OS MCP server (https://focxle.com/api/v1/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AFOS — Agentic Financial OS, and thousands of servers like it.
Across the catalogue