AI agents call get_citation 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 retrieves bibliographic metadata for papers—a pure read operation with no side effects. The user queries the system to obtain a formatted citation, but no data is created, modified, or deleted. The sibling tools (get_paper, get_paper_content, list_* functions, query_rag, search_papers) all indicate this is a read-heavy research information retrieval system.
From the tool's definition Tool name: 'get_citation' | Description: 'Get BibTeX citation for a paper.' | This is a retrieval operation that fetches pre-existing citation metadata in BibTeX format without modifying, creating, or deleting any data.
Attacks that exploit this kind of access
Get BibTeX citation for a paper. 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_citation: 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_citation 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_citation 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_citation. 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_citation 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 →