Retrieve attachments (PDFs, videos, links) with optional project filters
AI agents call getAttachments to retrieve information from 42 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 existing attachments and metadata without creating, modifying, or deleting data. It performs a simple query against the 42 intranet API. The optional filtering parameters do not change the fundamental read-only nature of the operation.
From the tool's definition Tool name and description both indicate retrieval: "Retrieve attachments" with "optional project filters".
Attacks that exploit this kind of access
Retrieve attachments (PDFs, videos, links) with optional project filters. It is categorised as a Read tool in the 42 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the 42 MCP Server MCP server in PolicyLayer and add a rule for getAttachments: 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 42 MCP Server. Nothing to install.
getAttachments 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 getAttachments 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 getAttachments. 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.
getAttachments is provided by the 42 MCP Server MCP server (smizuoch/42-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 →