Fetches the OpenAPI/Swagger JSON spec for this API. Use this to discover endpoint paths, HTTP methods, and request body schemas before calling request().
AI agents call fetch_spec to retrieve information from Rest Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns API metadata (OpenAPI/Swagger specification) without modifying, deleting, or executing any operations. It is purely informational and discovery-focused, typical of Read category tools. The low severity reflects that obtaining API schema documentation poses minimal risk even if misused by an agent.
From the tool's definition Fetches the OpenAPI/Swagger JSON spec for this API. Use this to discover endpoint paths, HTTP methods, and request body schemas — a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access fetch_spec gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rest Api, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_spec:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_spec": {}
}
}fetch_spec 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.
Fetches the OpenAPI/Swagger JSON spec for this API. Use this to discover endpoint paths, HTTP methods, and request body schemas before calling request(). It is categorised as a Read tool in the Rest Api MCP Server, which means it retrieves data without modifying state.
Register the Rest Api MCP server in PolicyLayer and add a rule for fetch_spec: 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 Rest Api. Nothing to install.
fetch_spec 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 fetch_spec 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 fetch_spec. 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.
fetch_spec is provided by the Rest Api MCP server (muhammed-abdelghany/rest_api_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rest Api, 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 Rest Api tools catalogued and risk-classified — across an index of 43,000+ MCP servers.