AI agents use add_key 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.
The tool creates or adds data to code structures reversibly through AST-based modification. This is a Write operation rather than Destructive because it adds new content rather than deleting or overwriting existing data, and the effect is reversible. Severity is medium because incorrect key additions could break code structure or introduce bugs, but the effect is localized to a single key insertion and can be undone.
From the tool's definition Tool name is 'add_key' with empty description. Sibling tools on the server include 'add_cell', 'add_field', 'add_import', 'add_method', 'add_parameter', 'add_top_level' — all Write operations that create or modify code structures via AST manipulation.
Documented attack patterns abuse exactly the kind of access add_key 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_key:
{
"version": "1",
"default": "deny",
"tools": {
"add_key": {
"limits": [
{
"counter": "add_key_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_key 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_key. 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_key: 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_key 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_key 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_key. 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_key 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.