Toggle boolean value at path. Args: key: The name of the key path: The path in the JSON document Returns: New boolean value or error message
AI agents use json_toggle to create or update resources in AWS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AWS environment.
This tool modifies existing data (toggles a boolean value) in a JSON document, which is a reversible write operation. It changes state but does not delete data or execute code, placing it firmly in the Write category. Severity is medium because toggling boolean flags in configuration or state documents (especially on an AWS server) could affect service behavior, access controls, or feature flags.
From the tool's definition Toggle boolean value at path — modifies a boolean value in a JSON document at a specified path
Documented attack patterns abuse exactly the kind of access json_toggle gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS, and nothing reaches the server without passing your rules. This is the rule we recommend for json_toggle:
{
"version": "1",
"default": "deny",
"tools": {
"json_toggle": {
"limits": [
{
"counter": "json_toggle_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}json_toggle 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.
Toggle boolean value at path. Args: key: The name of the key path: The path in the JSON document Returns: New boolean value or error message. It is categorised as a Write tool in the AWS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AWS MCP server in PolicyLayer and add a rule for json_toggle: 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 AWS. Nothing to install.
json_toggle 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 json_toggle 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 json_toggle. 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.
json_toggle is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS, 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.
300 AWS tools catalogued and risk-classified — across an index of 43,000+ MCP servers.