Create a new feature
AI agents use create_feature to create or update resources in Follow Plan MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Follow Plan MCP Server environment.
Creating a feature is a Write operation—it adds new data to the project planning system that can be modified or removed later. It has no destructive, financial, or code-execution implications. The blast radius is low since feature creation is a normal, reversible project management operation.
From the tool's definition Tool name 'create_feature' and description 'Create a new feature' indicate data creation. The server description confirms it handles 'feature specification with SQLite persistence', showing this creates reversible records in the database.
Attacks that exploit this kind of access
Create a new feature. It is categorised as a Write tool in the Follow Plan MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Follow Plan MCP Server MCP server in PolicyLayer and add a rule for create_feature: 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 Follow Plan MCP Server. Nothing to install.
create_feature 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_feature 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_feature. 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_feature is provided by the Follow Plan MCP Server MCP server (vibeclasses/follow-plan-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 →