搜索 schema 定義，支援模糊搜索和類型過濾
AI agents call search_schemas 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 queries schema information from Swagger/OpenAPI documents. It performs read-only operations (search, filter) with no side effects on data. The fuzzy search and type filtering are non-destructive query operations. Even though schemas could theoretically contain sensitive information, the tool itself is purely informational retrieval with no capability to modify or execute code.
From the tool's definition Tool name 'search_schemas' and description indicate searching/querying schema definitions with fuzzy search and type filtering capabilities. No modification, execution, or deletion operations are described.
Attacks that exploit this kind of access
搜索 schema 定義，支援模糊搜索和類型過濾. 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 search_schemas: 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.
search_schemas 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 search_schemas 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 search_schemas. 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.
search_schemas 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 →