Create a new thinking step in the sequential process
AI agents use create_step to create or update resources in Mcp Asana Minimal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Asana Minimal environment.
This tool creates a new step, which modifies the state of a sequential process by adding a reversible entry. It is a Write operation—data is created and can be undone/modified.
From the tool's definition Tool name 'create_step' and description 'Create a new thinking step in the sequential process' indicate creation of data (a step in a workflow/process).
Attacks that exploit this kind of access
Create a new thinking step in the sequential process. It is categorised as a Write tool in the Mcp Asana Minimal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Asana Minimal MCP server in PolicyLayer and add a rule for create_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 Mcp Asana Minimal. Nothing to install.
create_step is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_step is provided by the Mcp Asana Minimal MCP server (mcp-asana-minimal). 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 →