AI agents use yapi_save_api to create or update resources in Yapi Auto MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yapi Auto MCP Server environment.
This tool creates or modifies API documentation metadata in the YApi platform. The operations are reversible (documentation can be updated or corrected later), making it Write rather than Destructive. Severity is medium because misuse could corrupt API documentation, misleading developers, but the blast radius is contained to documentation records and doesn't directly execute code or delete data irreversibly.
From the tool's definition Tool description states '新增或更新YApi中的接口信息' (create or update API interface information in YApi). The verbs '新增' (create/add) and '更新' (update) indicate reversible data modification.
Documented attack patterns abuse exactly the kind of access yapi_save_api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Yapi Auto MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for yapi_save_api:
{
"version": "1",
"default": "deny",
"tools": {
"yapi_save_api": {
"limits": [
{
"counter": "yapi_save_api_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}yapi_save_api 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.
新增或更新YApi中的接口信息. It is categorised as a Write tool in the Yapi Auto MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Yapi Auto MCP Server MCP server in PolicyLayer and add a rule for yapi_save_api: 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 Yapi Auto MCP Server. Nothing to install.
yapi_save_api 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 yapi_save_api 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 yapi_save_api. 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.
yapi_save_api is provided by the Yapi Auto MCP Server MCP server (lzsheng/yapi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Yapi Auto MCP Server, 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.
5 Yapi Auto MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.