AI agents call workflow_guide to retrieve information from Substrate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents workflow information to the user. The verb 'Get' combined with 'guidance' (informational content) confirms it performs a read-only query with no capability to modify, execute, delete, or otherwise alter system state. No arguments are mentioned that would suggest code execution or data modification.
From the tool's definition Tool name 'workflow_guide' and description 'Get step-by-step guidance for a specific workflow' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get step-by-step guidance for a specific workflow. It is categorised as a Read tool in the Substrate MCP Server, which means it retrieves data without modifying state.
Register the Substrate MCP server in PolicyLayer and add a rule for workflow_guide: 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 Substrate. Nothing to install.
workflow_guide 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_guide 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_guide. 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_guide is provided by the Substrate MCP server (ivan-saorin/substrate). 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 →