Force-refetch Swagger documentation data and update the cache. Use this after the documentation has been updated (interfaces added or modified) to fetch the latest data. Parameters: - source (optional): Service name. Omit to refresh all services. Returns: Refresh results, including success/failur...
AI agents use swagger_refresh_cache to create or update resources in Internal Swagger — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Internal Swagger environment.
This tool modifies the cache state by refreshing and updating documentation data. While it doesn't delete data (ruling out Destructive) or execute arbitrary code (Execute), it does write/update the cache, making it a Write operation. Severity is medium because cache corruption could disrupt API documentation availability for downstream users, but the operation is reversible by re-running the refresh. Confidence is 0.
From the tool's definition Force-refetch Swagger documentation data and update the cache indicates modifying cached data. The description states it updates the cache with latest data after documentation changes, which is a reversible write operation on the internal cache layer.
Attacks that exploit this kind of access
Force-refetch Swagger documentation data and update the cache. Use this after the documentation has been updated (interfaces added or modified) to fetch the latest data. Parameters: - source (optional): Service name. Omit to refresh all services. Returns: Refresh results, including success/failure status and updated interface counts. It is categorised as a Write tool in the Internal Swagger MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Internal Swagger MCP server in PolicyLayer and add a rule for swagger_refresh_cache: 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 Internal Swagger. Nothing to install.
swagger_refresh_cache is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the swagger_refresh_cache 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 swagger_refresh_cache. 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.
swagger_refresh_cache is provided by the Internal Swagger MCP server (zhangwanli09/internal-swagger-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 →