Analyze Odos trading performance with optional filtering
AI agents call get_past_performance to retrieve information from Odos 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 and analyzes existing performance metrics/historical data. The use of 'get_' prefix and 'analyze' (which implies data inspection rather than action) confirm Read classification. There are no indications of state changes, code execution, deletions, or financial transactions. The optional filtering suggests querying capabilities.
From the tool's definition Tool name 'get_past_performance' and description 'Analyze Odos trading performance with optional filtering' indicate retrieval and analysis of historical performance data without modification or execution capabilities.
Attacks that exploit this kind of access
Analyze Odos trading performance with optional filtering. It is categorised as a Read tool in the Odos MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Odos MCP Server MCP server in PolicyLayer and add a rule for get_past_performance: 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 Odos MCP Server. Nothing to install.
get_past_performance 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 get_past_performance 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 get_past_performance. 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.
get_past_performance is provided by the Odos MCP Server MCP server (odos-xyz/odos-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 →