AI agents use upload_object 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.
This tool creates or modifies data in QuantConnect's Object Store, which is reversible (files can be deleted or overwritten later). While high severity due to potential for uploading malicious code, configuration files, or large volumes of data that could disrupt services, it does not irreversibly destroy data (Destructive), execute arbitrary operations (Execute), or move money (Financial).
From the tool's definition Tool name 'upload_object' combined with description 'Upload files to the Object Store' directly indicates file creation/modification in persistent storage.
Documented attack patterns abuse exactly the kind of access upload_object 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 upload_object:
{
"version": "1",
"default": "deny",
"tools": {
"upload_object": {
"limits": [
{
"counter": "upload_object_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upload_object 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.
Upload files to the Object Store. 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 upload_object: 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.
upload_object 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 upload_object 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 upload_object. 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.
upload_object 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.