Check if DeepSeek AI features are available and configured
AI agents call ai_status to retrieve information from Filopastry without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple status check or query to determine the availability and configuration state of AI features. It retrieves information without modifying, creating, executing, or deleting any data. Status checks and availability queries are read operations with minimal security risk.
From the tool's definition Tool name 'ai_status' and description 'Check if DeepSeek AI features are available and configured' indicate a query/status check operation with no side effects.
Attacks that exploit this kind of access
Check if DeepSeek AI features are available and configured. It is categorised as a Read tool in the Filopastry MCP Server, which means it retrieves data without modifying state.
Register the Filopastry MCP server in PolicyLayer and add a rule for ai_status: 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 Filopastry. Nothing to install.
ai_status 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 ai_status 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 ai_status. 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.
ai_status is provided by the Filopastry MCP server (youwenshao/filopastry). 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 →