AI agents call get-document 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 document data and optionally exports it as an image. It performs a read-only query operation without creating, modifying, deleting, or executing any changes to the underlying data. The blast radius of misuse is minimal—an attacker could view documents they shouldn't access, but cannot alter or destroy them. This is a straightforward Read classification.
From the tool's definition Tool name is 'get-document' and description states it 'Get[s] a specific Lucid document by its ID' and 'Supports image export'. These are retrieval operations with no modification, deletion, or side effects.
Attacks that exploit this kind of access
Get a specific Lucid document by its ID. Extract document ID from Lucid URL or use known document ID. Supports image export. 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: 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 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 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. 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 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 →