AI agents call get_paper_content to retrieve information from Verbatim without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a data retrieval operation on academic papers. It queries and fetches document content without creating, modifying, deleting, or executing any code. The operation is read-only, non-destructive, and has minimal security risk. A language model misusing this tool could only retrieve paper content it has access to, with no ability to modify the underlying data or trigger external side effects.
From the tool's definition Tool retrieves full paper content in markdown format by ID. The name 'get_paper' and description 'Get full paper content' indicate a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
Get full paper content (markdown) by id. It is categorised as a Read tool in the Verbatim MCP Server, which means it retrieves data without modifying state.
Register the Verbatim MCP server in PolicyLayer and add a rule for get_paper_content: 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 Verbatim. Nothing to install.
get_paper_content 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_paper_content 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_paper_content. 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_paper_content is provided by the Verbatim MCP server (krlabsorg/verbatim-mcp). 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 →