Fetch data from a ${config.name} API endpoint (GET only), returning only the fields you select via GraphQL.
AI agents call query_api to retrieve information from Anyapi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves data via GET requests only with no side effects. While the underlying API could theoretically expose sensitive data depending on what endpoint is queried, the tool itself is fundamentally a read operation with no capability to modify, delete, or execute code. The 'GET only' restriction and GraphQL-style field selection further confirm this is a safe retrieval mechanism.
From the tool's definition Tool description states 'Fetch data from a ${config.name} API endpoint (GET only)', explicitly limiting to GET requests with no mutation or deletion capabilities. Field selection is read-only.
Documented attack patterns abuse exactly the kind of access query_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 query_api:
{
"version": "1",
"default": "deny",
"tools": {
"query_api": {}
}
}query_api is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetch data from a ${config.name} API endpoint (GET only), returning only the fields you select via GraphQL. It is categorised as a Read tool in the Anyapi MCP Server, which means it retrieves data without modifying state.
Register the Anyapi MCP server in PolicyLayer and add a rule for query_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.
query_api is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the query_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 query_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.
query_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.