Write data to a ${config.name} API endpoint (POST/PUT/PATCH/DELETE).
AI agents call mutate_api to permanently remove resources in Anyapi — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the tool primarily performs Write operations (POST/PUT/PATCH), it explicitly includes DELETE as a supported method. DELETE is inherently destructive and irreversible. Given that this is a universal API tool that can target any endpoint, an AI agent could accidentally or maliciously delete critical data.
From the tool's definition Tool description explicitly lists POST/PUT/PATCH/DELETE HTTP methods. DELETE operations are irreversible data destruction. PUT/PATCH can overwrite existing data. The tool is generic and operates on user-specified endpoints without built-in constraints.
Documented attack patterns abuse exactly the kind of access mutate_api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Anyapi, and nothing reaches the server without passing your rules. This is the rule we recommend for mutate_api:
{
"version": "1",
"default": "deny",
"hide": [
"mutate_api"
]
}mutate_api disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Write data to a ${config.name} API endpoint (POST/PUT/PATCH/DELETE). It is categorised as a Destructive tool in the Anyapi MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Anyapi MCP server in PolicyLayer and add a rule for mutate_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 Anyapi. Nothing to install.
mutate_api is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the mutate_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 mutate_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.
mutate_api is provided by the Anyapi MCP server (quiloos39/anyapi-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Anyapi, 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 Anyapi tools catalogued and risk-classified — across an index of 43,000+ MCP servers.