Save a completed workflow run as a project workflow and skill.
AI agents use workflow_save to create or update resources in Codex Workflows MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codex Workflows MCP Server environment.
The tool persists data (workflow and skill definitions) in a reversible manner. It does not execute arbitrary code, delete data, or move money. While it modifies the project state by adding new workflows/skills, this is a standard write operation.
From the tool's definition Tool description states "Save a completed workflow run as a project workflow and skill" — this creates or stores new workflow and skill artifacts in the system.
Documented attack patterns abuse exactly the kind of access workflow_save 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_save:
{
"version": "1",
"default": "deny",
"tools": {
"workflow_save": {
"limits": [
{
"counter": "workflow_save_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}workflow_save 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.
Save a completed workflow run as a project workflow and skill. It is categorised as a Write tool in the Codex Workflows MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codex Workflows MCP Server MCP server in PolicyLayer and add a rule for workflow_save: 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_save 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 workflow_save 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_save. 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_save 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.