AI agents use add_import_name to create or update resources in Ast Editor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ast Editor environment.
This tool creates or modifies import statements in source files, which is a reversible code modification (Write category). Severity is medium because injecting malicious imports could compromise code execution context, but the operation itself is reversible. Confidence is 0.85 rather than higher because the tool description is empty, requiring inference from the name and sibling tools.
From the tool's definition Tool name 'add_import_name' suggests adding/modifying import statements in code files. Server description indicates tools 'edit files surgically via Abstract Syntax Trees' and sibling tools include 'add_import', 'add_method', 'add_parameter'—all Write…
Documented attack patterns abuse exactly the kind of access add_import_name gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ast Editor, and nothing reaches the server without passing your rules. This is the rule we recommend for add_import_name:
{
"version": "1",
"default": "deny",
"tools": {
"add_import_name": {
"limits": [
{
"counter": "add_import_name_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_import_name stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
add_import_name. It is categorised as a Write tool in the Ast Editor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ast Editor MCP server in PolicyLayer and add a rule for add_import_name: 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 Ast Editor. Nothing to install.
add_import_name 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 add_import_name 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 add_import_name. 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.
add_import_name is provided by the Ast Editor MCP server (kambleakash0/agent-skills). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ast Editor, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
59 Ast Editor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.