Read workflow JSONL events after a cursor.
AI agents call workflow_events to retrieve information from Codex Workflows MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical workflow event data in JSONL format starting from a specified cursor position. It is a pure data retrieval operation with no capability to modify, execute, or delete data. The blast radius of misuse is minimal—an agent could only access workflow event logs that already exist, potentially revealing operational details but causing no direct harm or system changes.
From the tool's definition Tool description explicitly states 'Read workflow JSONL events after a cursor.' The verb 'read' and the passive nature of retrieving sequential event logs indicate no side effects or modifications.
Documented attack patterns abuse exactly the kind of access workflow_events gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codex Workflows MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for workflow_events:
{
"version": "1",
"default": "deny",
"tools": {
"workflow_events": {}
}
}workflow_events 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.
Read workflow JSONL events after a cursor. It is categorised as a Read tool in the Codex Workflows MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Codex Workflows MCP Server MCP server in PolicyLayer and add a rule for workflow_events: 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 Codex Workflows MCP Server. Nothing to install.
workflow_events 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_events 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_events. 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_events is provided by the Codex Workflows MCP Server MCP server (robzilla1738/codex-workflows). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Codex Workflows MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 Codex Workflows MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.