AI agents call fetch_multiple to retrieve information from BibTeX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve multiple academic references/citations from the sources listed in the server description. Fetching data with no side effects is classified as Read. The blast radius of misuse is minimal since it only queries public academic databases and returns citation information, which cannot cause harm or unintended state changes.
From the tool's definition Tool name 'fetch_multiple' combined with server context indicating it searches and retrieves academic references from multiple sources (arXiv, DBLP, Semantic Scholar, OpenAlex).
Documented attack patterns abuse exactly the kind of access fetch_multiple gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and BibTeX MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_multiple:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_multiple": {}
}
}fetch_multiple 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.
fetch_multiple. It is categorised as a Read tool in the BibTeX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the BibTeX MCP Server MCP server in PolicyLayer and add a rule for fetch_multiple: 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 BibTeX MCP Server. Nothing to install.
fetch_multiple 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 fetch_multiple 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 fetch_multiple. 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.
fetch_multiple is provided by the BibTeX MCP Server MCP server (xeophon/bibtex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from BibTeX MCP Server, 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.
4 BibTeX MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.