AI agents call list_nodit_api_categories to retrieve information from Nodit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that enumerates available API categories for informational purposes. It retrieves metadata about the API structure without creating, modifying, executing, deleting, or moving any data. The tool serves as a discovery/enumeration mechanism with no destructive or operational capabilities.
From the tool's definition Tool name is 'list_nodit_api_categories' with description stating it 'Lists available Nodit API categories'. The verb 'list' and 'lists' indicate query/retrieval of metadata with no side effects.
Attacks that exploit this kind of access
Lists available Nodit API categories from Nodit Blockchain Context. To use the Nodit API tool, you must first call this tool. It is categorised as a Read tool in the Nodit MCP Server, which means it retrieves data without modifying state.
Register the Nodit MCP server in PolicyLayer and add a rule for list_nodit_api_categories: 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 Nodit. Nothing to install.
list_nodit_api_categories 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 list_nodit_api_categories 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 list_nodit_api_categories. 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.
list_nodit_api_categories is provided by the Nodit MCP server (@noditlabs/nodit-mcp-server). 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 →