Compare the current instance\
AI agents call get_schema_diff 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 compares schema data without creating, modifying, deleting, or executing operations. It is purely informational—comparing schemas to identify differences is a read-only operation with no side effects on the Directus instance or its data.
From the tool's definition Tool name 'get_schema_diff' and functionality to 'Compare the current instance' indicates retrieval and comparison of schema information with no modification capabilities.
Attacks that exploit this kind of access
Compare the current instance\. 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 get_schema_diff: 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.
get_schema_diff 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 get_schema_diff 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 get_schema_diff. 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.
get_schema_diff is provided by the Directus MCP Server MCP server (skeyelab/directus-mcp-server). 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 →