save_symphony
AI agents use save_symphony to create or update resources in Composer Trade — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Composer Trade environment.
This tool modifies investment strategy configurations reversibly. It creates or updates strategy data (symphonies) without executing trades or permanently deleting data, placing it in Write. Severity is high because saved strategies directly influence trading behavior and portfolio composition.
From the tool's definition Tool name 'save_symphony' on a server that 'create[s], backtest[s], and trade[s] automated investing strategies (symphonies).' The verb 'save' indicates creation or modification of strategy definitions that persist.
Attacks that exploit this kind of access
save_symphony. It is categorised as a Write tool in the Composer Trade MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Composer Trade MCP server in PolicyLayer and add a rule for save_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.
save_symphony 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 save_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 save_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.
save_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 →