backtest_symphony
AI agents invoke backtest_symphony to trigger actions in Composer Trade. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Based on the server context and sibling tool naming, this tool likely runs a backtest (simulation) of a symphony/strategy. Backtesting executes a computational process against historical data but does not move money or modify live data. It falls under Execute as it triggers an external computation. Confidence is low due to empty description.
From the tool's definition Tool name 'backtest_symphony' on a server that 'backtests automated investing strategies'; sibling tool 'backtest_symphony_by_id' suggests this runs a backtest simulation.
Attacks that exploit this kind of access
backtest_symphony. It is categorised as a Execute tool in the Composer Trade MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Composer Trade MCP server in PolicyLayer and add a rule for backtest_symphony: 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 Composer Trade. Nothing to install.
backtest_symphony is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the backtest_symphony 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 backtest_symphony. 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.
backtest_symphony is provided by the Composer Trade MCP server (tanwithme/composer-trade-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 →