AI agents call embeddings_health to retrieve information from Atlas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs health checks and retrieves configuration information about the embeddings service. It has no side effects, does not modify data, and is purely informational in nature. It falls squarely into the Read category as it queries service state without any capability to create, modify, or delete data.
From the tool's definition Tool name 'embeddings_health' and description 'Check embeddings service health and configuration' indicate a read-only diagnostic operation that retrieves status information without modifying any data.
Attacks that exploit this kind of access
Check embeddings service health and configuration. It is categorised as a Read tool in the Atlas MCP Server, which means it retrieves data without modifying state.
Register the Atlas MCP server in PolicyLayer and add a rule for embeddings_health: 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 Atlas. Nothing to install.
embeddings_health 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 embeddings_health 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 embeddings_health. 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.
embeddings_health is provided by the Atlas MCP server (rsanandres/atlas_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 →