AI agents call extract_code to retrieve information from McFlow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool extracts code from workflow nodes into separate files, which is primarily a read/export operation. However, it does write files to disk (workflows/nodes/), which could be considered a Write action. The description emphasizes 'better editing' suggesting it's a helper/organization tool. Since it creates new files on disk, Write is arguably more accurate, but the core action is extraction (reading and copying).
From the tool's definition Extract code nodes to separate files in workflows/nodes/ for better editing
Attacks that exploit this kind of access
Extract code nodes to separate files in workflows/nodes/ for better editing. It is categorised as a Read tool in the McFlow MCP Server, which means it retrieves data without modifying state.
Register the McFlow MCP server in PolicyLayer and add a rule for extract_code: 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 McFlow. Nothing to install.
extract_code 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 extract_code 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 extract_code. 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.
extract_code is provided by the McFlow MCP server (mckinleymedia/mcflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →