AI agents call import_examples_from_project to retrieve information from Tron without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool imports examples from an external codebase, which is primarily a read/fetch operation. However, combined with 'add_verified_example' sibling tool, imported examples may be written to a local store. The description is vague about side effects, lowering confidence. The primary action appears to be reading/fetching data from an external source.
From the tool's definition 'Import verified examples from netts.io project codebase' — reads/imports code examples from an external project
Attacks that exploit this kind of access
Import verified examples from netts.io project codebase. It is categorised as a Read tool in the Tron MCP Server, which means it retrieves data without modifying state.
Register the Tron MCP server in PolicyLayer and add a rule for import_examples_from_project: 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 Tron. Nothing to install.
import_examples_from_project 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 import_examples_from_project 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 import_examples_from_project. 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.
import_examples_from_project is provided by the Tron MCP server (netts-official/tron_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 →