AI agents call get-document-tabs to retrieve information from Lucid without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about document pages (tabs) with no side effects. It queries document structure information without creating, modifying, deleting, or executing operations. The explicit exclusion of detailed content confirms read-only behavior. Confidence is high due to clear and specific description of retrieval-only functionality.
From the tool's definition Tool name 'get-document-tabs' and description 'Get metadata about all tabs (pages)' and 'Returns compact JSON with document info and page metadata' clearly indicate retrieval only. Explicitly excludes content shapes and lines.
Attacks that exploit this kind of access
Get metadata about all tabs (pages) in a Lucid document. Returns compact JSON with document info and page metadata (id, title, index) only - excludes shapes, lines, and other content. It is categorised as a Read tool in the Lucid MCP Server, which means it retrieves data without modifying state.
Register the Lucid MCP server in PolicyLayer and add a rule for get-document-tabs: 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 Lucid. Nothing to install.
get-document-tabs 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-document-tabs 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-document-tabs. 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-document-tabs is provided by the Lucid MCP server (lucid-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 →