AI agents use replace_rule_save to create or update resources in Legado — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Legado environment.
The tool creates or modifies replace rules within the Legado system, which is a reversible data operation. While the description is empty (lowering confidence slightly), the name and server context clearly indicate a write operation. It's not destructive because replace rules can be modified or deleted later.
From the tool's definition Tool name 'replace_rule_save' indicates it saves/persists replace rules. Context shows this is part of Legado's replace rules management system. The 'save' operation modifies data in the Legado system.
Documented attack patterns abuse exactly the kind of access replace_rule_save gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Legado, and nothing reaches the server without passing your rules. This is the rule we recommend for replace_rule_save:
{
"version": "1",
"default": "deny",
"tools": {
"replace_rule_save": {
"limits": [
{
"counter": "replace_rule_save_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}replace_rule_save 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.
replace_rule_save. It is categorised as a Write tool in the Legado MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Legado MCP server in PolicyLayer and add a rule for replace_rule_save: 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 Legado. Nothing to install.
replace_rule_save 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 replace_rule_save 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 replace_rule_save. 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.
replace_rule_save is provided by the Legado MCP server (joestar817/legado-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Legado, 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.
31 Legado tools catalogued and risk-classified — across an index of 43,000+ MCP servers.