AI agents use api-automation to create or update resources in Feuse — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Feuse environment.
This tool reads/understands backend API documentation and generates (writes/creates) multiple code artifacts: type definitions, constants, mock data, and request functions. It creates new files/code, which is a Write operation. No destructive, financial, or execution of arbitrary commands is implied.
From the tool's definition 自动生成接口类型、地址常量、mock数据、请求函数等 (automatically generates interface types, address constants, mock data, request functions)
Documented attack patterns abuse exactly the kind of access api-automation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Feuse, and nothing reaches the server without passing your rules. This is the rule we recommend for api-automation:
{
"version": "1",
"default": "deny",
"tools": {
"api-automation": {
"limits": [
{
"counter": "api-automation_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}api-automation 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.
理解后端接口文档自动生成接口类型、地址常量、mock数据、请求函数等. It is categorised as a Write tool in the Feuse MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Feuse MCP server in PolicyLayer and add a rule for api-automation: 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 Feuse. Nothing to install.
api-automation 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 api-automation 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 api-automation. 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.
api-automation is provided by the Feuse MCP server (panzer-jack/feuse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Feuse tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Feuse tools catalogued and risk-classified — across an index of 42,500+ MCP servers.