AI agents call aevo_get_positions to retrieve information from Aevo-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix and 'positions' noun indicate this is a read-only query of existing trading positions. It retrieves data about the user's portfolio/account state without modifying, deleting, or executing trades. Severity is medium rather than low because position data can inform adversarial trading decisions if leaked, though the tool itself performs no destructive actions.
From the tool's definition Tool name 'aevo_get_positions' indicates a retrieval operation (get). Server context confirms it retrieves account/trading positions from the Aevo trading platform. Description is empty, reducing confidence slightly.
Attacks that exploit this kind of access
aevo_get_positions. It is categorised as a Read tool in the Aevo-MCP MCP Server, which means it retrieves data without modifying state.
Register the Aevo- MCP server in PolicyLayer and add a rule for aevo_get_positions: 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 Aevo-MCP. Nothing to install.
aevo_get_positions 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 aevo_get_positions 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 aevo_get_positions. 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.
aevo_get_positions is provided by the Aevo- MCP server (ribbon-finance/aevo-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 →