Create a new category.
AI agents use create_category_tool to create or update resources in MCP Feed Reader — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Feed Reader environment.
This tool creates a new category in the feed reader's SQLite backend. Creation of data records is a Write operation. Severity is low because the blast radius of creating an unwanted category is minimal—it does not delete data, execute external code, or affect financial systems. The user can delete the category afterward.
From the tool's definition Tool name 'create_category_tool' and description 'Create a new category' indicate creation of a new data record. The action is reversible (the sibling delete_category_tool confirms deletion is possible), with no side effects beyond adding a database entry.
Attacks that exploit this kind of access
Create a new category. It is categorised as a Write tool in the MCP Feed Reader MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Feed Reader MCP server in PolicyLayer and add a rule for create_category_tool: 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 Feed Reader. Nothing to install.
create_category_tool 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_category_tool 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_category_tool. 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_category_tool is provided by the MCP Feed Reader MCP server (pypi:mcp-feed-reader-crunchtools). 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 →