Query multiple documents from a content type. By default, returns summary fields only (excludes large content fields like
AI agents call find_many to retrieve information from Strapi Content MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves data without creating, modifying, deleting, or executing operations. It has minimal blast radius—a misused query returns data the agent may not have authorization to see, but causes no side effects or state changes. Classified as Read with low severity.
From the tool's definition Tool name 'find_many' and description 'Query multiple documents from a content type' indicate a retrieval operation with no modification capability. The phrase 'returns summary fields only' confirms it is read-only.
Attacks that exploit this kind of access
Query multiple documents from a content type. By default, returns summary fields only (excludes large content fields like. It is categorised as a Read tool in the Strapi Content MCP MCP Server, which means it retrieves data without modifying state.
Register the Strapi Content MCP server in PolicyLayer and add a rule for find_many: 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 Strapi Content MCP. Nothing to install.
find_many 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 find_many 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 find_many. 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.
find_many is provided by the Strapi Content MCP server (paulbratslavsky/strapi-content-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 →