Download and convert the PDF of a paper to markdown format from a direct PDF URL. Returns full paper content parsed from the PDF including title, abstract, sections, and references.
AI agents call get_paper_content_by_url to retrieve information from Paperclip without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and transforms existing content (PDF to markdown) without creating, modifying, deleting, or executing any operations. It is purely a data retrieval function accessing publicly available research papers. The severity is low because misuse would only result in accessing research content that is typically intended to be freely available.
From the tool's definition Tool description states it 'Download and convert the PDF of a paper to markdown format' and 'Returns full paper content parsed from the PDF'. These are retrieval and conversion operations with no modification, deletion, or execution of code.
Documented attack patterns abuse exactly the kind of access get_paper_content_by_url gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Paperclip, and nothing reaches the server without passing your rules. This is the rule we recommend for get_paper_content_by_url:
{
"version": "1",
"default": "deny",
"tools": {
"get_paper_content_by_url": {}
}
}get_paper_content_by_url is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Download and convert the PDF of a paper to markdown format from a direct PDF URL. Returns full paper content parsed from the PDF including title, abstract, sections, and references. It is categorised as a Read tool in the Paperclip MCP Server, which means it retrieves data without modifying state.
Register the Paperclip MCP server in PolicyLayer and add a rule for get_paper_content_by_url: 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 Paperclip. Nothing to install.
get_paper_content_by_url 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_by_url 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_by_url. 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_by_url is provided by the Paperclip MCP server (matsjfunke/paperclip). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Paperclip, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Paperclip tools catalogued and risk-classified — across an index of 43,000+ MCP servers.