This tool lists all available source urls where an OpenAPI spec can be fetched.
AI agents call list_openapi_spec_sources to retrieve information from SushiMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and returns a list of available sources. There are no side effects, no data modification, no code execution, and no resource consumption beyond retrieving metadata. The blast radius of misuse is minimal—an attacker would only gain knowledge of available OpenAPI spec sources, which is non-sensitive operational metadata.
From the tool's definition The tool 'lists all available source urls where an OpenAPI spec can be fetched' — it retrieves and enumerates data with no modification or execution capability.
Documented attack patterns abuse exactly the kind of access list_openapi_spec_sources gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SushiMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for list_openapi_spec_sources:
{
"version": "1",
"default": "deny",
"tools": {
"list_openapi_spec_sources": {}
}
}list_openapi_spec_sources 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.
This tool lists all available source urls where an OpenAPI spec can be fetched. It is categorised as a Read tool in the SushiMCP MCP Server, which means it retrieves data without modifying state.
Register the Sushi MCP server in PolicyLayer and add a rule for list_openapi_spec_sources: 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 SushiMCP. Nothing to install.
list_openapi_spec_sources 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 list_openapi_spec_sources 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 list_openapi_spec_sources. 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.
list_openapi_spec_sources is provided by the Sushi MCP server (maverickg59/sushimcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SushiMCP, 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.
7 SushiMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.