AI agents use update_optimization to create or update resources in QuantConnect — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your QuantConnect environment.
The tool creates or modifies data in a reversible manner. Renaming an optimization is a write operation that can be undone by renaming it again. It does not execute code, delete data irreversibly, or move money. The medium severity reflects that modifying optimization configurations could affect trading strategy backtests or live deployments, but the action itself is non-destructive and can be corrected.
From the tool's definition Tool name is 'update_optimization' and description states 'Update the name of an optimization.' This modifies existing data (the optimization's name) reversibly.
Documented attack patterns abuse exactly the kind of access update_optimization gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and QuantConnect, and nothing reaches the server without passing your rules. This is the rule we recommend for update_optimization:
{
"version": "1",
"default": "deny",
"tools": {
"update_optimization": {
"limits": [
{
"counter": "update_optimization_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_optimization stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update the name of an optimization. It is categorised as a Write tool in the QuantConnect MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the QuantConnect MCP server in PolicyLayer and add a rule for update_optimization: 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 QuantConnect. Nothing to install.
update_optimization 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 update_optimization 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 update_optimization. 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.
update_optimization is provided by the QuantConnect MCP server (quantconnect/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 64 QuantConnect tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
64 QuantConnect tools catalogued and risk-classified — across an index of 42,500+ MCP servers.