Check the health and operational status of The Aleph API
AI agents call thealeph_health_check to retrieve information from The Aleph MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
A health check retrieves the current operational status of a service without modifying, executing external code, deleting data, or moving money. It is a read-only diagnostic operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name and description indicate a health/status check operation: 'Check the health and operational status of The Aleph API'. This is a diagnostic query with no side effects.
Attacks that exploit this kind of access
Check the health and operational status of The Aleph API. It is categorised as a Read tool in the The Aleph MCP MCP Server, which means it retrieves data without modifying state.
Register the The Aleph MCP server in PolicyLayer and add a rule for thealeph_health_check: 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 The Aleph MCP. Nothing to install.
thealeph_health_check 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 thealeph_health_check 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 thealeph_health_check. 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.
thealeph_health_check is provided by the The Aleph MCP server (nu-aqualab/thealeph-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 →