AI agents call load_workflow to retrieve information from Shotter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and parses workflow configuration from a YAML file, returning its contents for inspection. It performs no write, deletion, code execution, or state modification. The sibling tools (ui_tap, ui_swipe, launch_app) perform the actual interactions; load_workflow only reads and interprets the workflow definition.
From the tool's definition load_workflow 'Load and parse a workflow YAML file. Returns steps, devices, and configuration.' — reads and parses file content with no mutation or execution side effects.
Attacks that exploit this kind of access
Load and parse a workflow YAML file. Returns steps, devices, and configuration. It is categorised as a Read tool in the Shotter MCP Server, which means it retrieves data without modifying state.
Register the Shotter MCP server in PolicyLayer and add a rule for load_workflow: 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 Shotter. Nothing to install.
load_workflow 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 load_workflow 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 load_workflow. 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.
load_workflow is provided by the Shotter MCP server (nathanstitt/shotter). 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 →