Convert a known DOI into a formatted, publication-ready citation string.
AI agents call resolve_citation to retrieve information from BioCite-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool takes a DOI as input and returns a formatted citation string. This is a read/fetch operation that queries external metadata (e.g., Crossref) and formats it. No data is created, modified, deleted, or transmitted to any writable destination. Severity is low because misuse could only result in incorrect citation formatting, with minimal blast radius.
From the tool's definition 'Convert a known DOI into a formatted, publication-ready citation string' — purely retrieves and formats metadata from an existing DOI with no side effects
Attacks that exploit this kind of access
Convert a known DOI into a formatted, publication-ready citation string. It is categorised as a Read tool in the BioCite-MCP MCP Server, which means it retrieves data without modifying state.
Register the BioCite- MCP server in PolicyLayer and add a rule for resolve_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 BioCite-MCP. Nothing to install.
resolve_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 resolve_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 resolve_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.
resolve_citation is provided by the BioCite- MCP server (muslus/biocite-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 →