Update collaborator information in a project.
AI agents use update_project_collaborator 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 (collaborator roles, permissions, or contact information) within a project. While reversible (collaborators can be re-updated or removed), it affects project access control and team composition, which could impact who can view sensitive trading strategies or algorithms. The blast radius includes potential unauthorized access grants or accidental removal of legitimate collaborators.
From the tool's definition Tool name 'update_project_collaborator' and description 'Update collaborator information in a project' indicate modification of project metadata and access control settings.
Documented attack patterns abuse exactly the kind of access update_project_collaborator 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_project_collaborator:
{
"version": "1",
"default": "deny",
"tools": {
"update_project_collaborator": {
"limits": [
{
"counter": "update_project_collaborator_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_project_collaborator 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 collaborator information in a project. 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_project_collaborator: 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_project_collaborator 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_project_collaborator 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_project_collaborator. 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_project_collaborator 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.