AI agents call detect-entities to retrieve information from Secure Embedding MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs analysis and pattern recognition on input text to identify sensitive entities (such as PII, credentials, etc.). It retrieves or extracts information from text without side effects—no data is created, modified, deleted, or executed. The operation is informational and reversible.
From the tool's definition Tool name 'detect-entities' and description 'Detect sensitive entities in text' indicate a read-only operation that analyzes and identifies patterns in provided text without modifying, executing, or deleting data.
Documented attack patterns abuse exactly the kind of access detect-entities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Secure Embedding MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for detect-entities:
{
"version": "1",
"default": "deny",
"tools": {
"detect-entities": {}
}
}detect-entities is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Detect sensitive entities in text. It is categorised as a Read tool in the Secure Embedding MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Secure Embedding MCP Server MCP server in PolicyLayer and add a rule for detect-entities: 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 Secure Embedding MCP Server. Nothing to install.
detect-entities 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 detect-entities 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 detect-entities. 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.
detect-entities is provided by the Secure Embedding MCP Server MCP server (mirrorsecai/mirror-vectax-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Secure Embedding MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Secure Embedding MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.