Collect results from completed workers without waiting for all to finish.
AI agents call workflow_collect_partial to retrieve information from OpenChrome without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool gathers/queries results from a workflow system. The verb 'collect' combined with 'without waiting' indicates polling or fetching completed work items, not creating, modifying, or deleting data. No external actions are triggered; it simply retrieves state. This is a Read operation with minimal blast radius.
From the tool's definition Tool name and description indicate data retrieval: 'Collect results from completed workers' — a passive aggregation of already-computed outputs with no modification, deletion, or side effects.
Documented attack patterns abuse exactly the kind of access workflow_collect_partial gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenChrome, and nothing reaches the server without passing your rules. This is the rule we recommend for workflow_collect_partial:
{
"version": "1",
"default": "deny",
"tools": {
"workflow_collect_partial": {}
}
}workflow_collect_partial is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Collect results from completed workers without waiting for all to finish. It is categorised as a Read tool in the OpenChrome MCP Server, which means it retrieves data without modifying state.
Register the OpenChrome MCP server in PolicyLayer and add a rule for workflow_collect_partial: 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 OpenChrome. Nothing to install.
workflow_collect_partial is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the workflow_collect_partial 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 workflow_collect_partial. 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.
workflow_collect_partial is provided by the OpenChrome MCP server (shaun0927/openchrome). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 106 OpenChrome tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
106 OpenChrome tools catalogued and risk-classified — across an index of 42,500+ MCP servers.