AI agents use create_contract to create or update resources in Ib Async — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ib Async environment.
The tool creates/instantiates trading contract specifications, which modifies the system state by adding new contract definitions. While contract creation itself is reversible (contracts can be deleted or modified), it is a precursor to trade execution and represents a Write operation. It does not execute trades (Execute category), nor does it move money (Financial), nor is it irreversible (Destructive).
From the tool's definition Tool is named 'create_contract' and description states 'Create a contract for trading' with support for multiple asset types (stock, option, future, forex, index, cfd, crypto, bond). This creates new trading contract objects.
Attacks that exploit this kind of access
Create a contract for trading. Types: stock, option, future, forex, index, cfd, crypto, bond. It is categorised as a Write tool in the Ib Async MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ib Async MCP server in PolicyLayer and add a rule for create_contract: 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 Ib Async. Nothing to install.
create_contract 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 create_contract 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 create_contract. 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.
create_contract is provided by the Ib Async MCP server (nadavgb-atom/ib-async-mcp). 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 →