Analyze relationships across collections
AI agents call analyze_relationships to retrieve information from Directus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and examines relationship metadata across Directus collections. No write, execute, destructive, or financial operations are performed. It is a read-only inspection tool with minimal security risk.
From the tool's definition Tool name 'analyze_relationships' and description 'Analyze relationships across collections' indicate a query/inspection operation. The verb 'analyze' implies reading and examining existing data structures without modification.
Attacks that exploit this kind of access
Analyze relationships across collections. It is categorised as a Read tool in the Directus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Directus MCP Server MCP server in PolicyLayer and add a rule for analyze_relationships: 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 Directus MCP Server. Nothing to install.
analyze_relationships 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 analyze_relationships 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 analyze_relationships. 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.
analyze_relationships is provided by the Directus MCP Server MCP server (staminna/mcp-server-claude). 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 →