get_next_step
AI agents call get_next_step to retrieve information from Engmanager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the next step in a development workflow—a query operation with no side effects. The empty description and the context of sibling read-only tools (get_, list_) suggest it returns workflow state or instructions without modifying or executing anything. No destructive, financial, or execute-like behavior is indicated.
From the tool's definition Tool name 'get_next_step' combined with sibling tools 'get_project_info', 'get_workflow_section', and 'list_workflow_steps' indicates read-only retrieval of workflow guidance information.
Attacks that exploit this kind of access
get_next_step. It is categorised as a Read tool in the Engmanager MCP Server, which means it retrieves data without modifying state.
Register the Engmanager MCP server in PolicyLayer and add a rule for get_next_step: 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 Engmanager. Nothing to install.
get_next_step 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 get_next_step 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 get_next_step. 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.
get_next_step is provided by the Engmanager MCP server (scarr7981/engmanager-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 →