Extract specific information from a workflow using OpenAI model
AI agents call extract-workflow-info to retrieve information from Scratchpad MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes information from an existing workflow without creating, modifying, or deleting data. The use of an LLM (OpenAI model) for extraction does not elevate the category—the underlying operation remains a non-destructive read. No blast radius from misuse beyond potential information disclosure of workflow contents.
From the tool's definition Tool name 'extract-workflow-info' and description state it 'Extract[s] specific information from a workflow', which is a retrieval operation with no side effects. The action is query-based information extraction, not modification or deletion.
Attacks that exploit this kind of access
Extract specific information from a workflow using OpenAI model. It is categorised as a Read tool in the Scratchpad MCP MCP Server, which means it retrieves data without modifying state.
Register the Scratchpad MCP server in PolicyLayer and add a rule for extract-workflow-info: 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 Scratchpad MCP. Nothing to install.
extract-workflow-info 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-workflow-info 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-workflow-info. 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-workflow-info is provided by the Scratchpad MCP server (pc035860/scratchpad-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 →