獲取特定 API 的完整資訊，自動解析所有相關 schemas
AI agents call get_api_info to retrieve information from Swagger Json without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and parses existing API documentation metadata. There is no indication it modifies, deletes, executes code, or performs financial operations. The description uses passive/retrieval language ('獲取' = retrieve/obtain, '自動解析' = automatically parse).
From the tool's definition Tool name 'get_api_info' combined with description indicating it 'retrieves' (獲取) and 'parses' API information from Swagger/OpenAPI documents. The server description emphasizes 'querying and processing' documentation without side effects.
Attacks that exploit this kind of access
獲取特定 API 的完整資訊，自動解析所有相關 schemas. It is categorised as a Read tool in the Swagger Json MCP Server, which means it retrieves data without modifying state.
Register the Swagger Json MCP server in PolicyLayer and add a rule for get_api_info: 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 Json. Nothing to install.
get_api_info 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 get_api_info 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 get_api_info. 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.
get_api_info is provided by the Swagger Json MCP server (llm-mcp-servers/swagger-json-mcp). 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 →