Get all API groups (tags) from the Swagger documentation
AI agents call list_api_groups to retrieve information from Swagger Mcp Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata (API group tags) from Swagger/OpenAPI documentation without modifying, executing, or deleting anything. It is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'list_api_groups' and description 'Get all API groups (tags) from the Swagger documentation' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get all API groups (tags) from the Swagger documentation. It is categorised as a Read tool in the Swagger Mcp Tool MCP Server, which means it retrieves data without modifying state.
Register the Swagger Mcp Tool MCP server in PolicyLayer and add a rule for list_api_groups: 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 Swagger Mcp Tool. Nothing to install.
list_api_groups 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_api_groups 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_api_groups. 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_api_groups is provided by the Swagger Mcp Tool MCP server (sdlbp/swagger-mcp-tool). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →