fetch_ib_data
AI agents call fetch_ib_data to retrieve information from IB Analytics MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves portfolio and account data from Interactive Brokers without modifying it. It is a Read operation. However, severity is elevated to 'high' because: (1) the data retrieved concerns financial portfolios and accounts (sensitive), (2) an AI agent with uncontrolled access could exfiltrate complete portfolio details including positions, holdings, and valuations, and (3) the blast radius includes…
From the tool's definition Tool name 'fetch_ib_data' combined with server description stating 'automated data fetching' indicates data retrieval. No description provided, but sibling tools are all analyze_* functions suggesting this is a supporting data fetch operation.
Attacks that exploit this kind of access
fetch_ib_data. It is categorised as a Read tool in the IB Analytics MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IB Analytics MCP Server MCP server in PolicyLayer and add a rule for fetch_ib_data: 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 Analytics MCP Server. Nothing to install.
fetch_ib_data 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 fetch_ib_data 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 fetch_ib_data. 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.
fetch_ib_data is provided by the IB Analytics MCP Server MCP server (knishioka/ib-sec-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 →