Search stories using the Content Delivery API with advanced filtering
AI agents call search-stories to retrieve information from MCP Storyblok Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search function queries and retrieves story data through an API without creating, modifying, deleting, or executing operations. This is a standard read operation with minimal risk when misused—worst case an agent retrieves unintended content it may already have access to.
From the tool's definition Tool name 'search-stories' and description 'Search stories using the Content Delivery API with advanced filtering' indicate a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
Search stories using the Content Delivery API with advanced filtering. It is categorised as a Read tool in the MCP Storyblok Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Storyblok Server MCP server in PolicyLayer and add a rule for search-stories: 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 MCP Storyblok Server. Nothing to install.
search-stories 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-stories 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-stories. 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-stories is provided by the MCP Storyblok Server MCP server (zerdos/mcp-storyblok-server). 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 →