find_related
AI agents call find_related to retrieve information from Ryogena Pubmed without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without an explicit description, the tool name and server context indicate this retrieves or queries related literature data. No write, execute, destructive, or financial operations are implied. The minimal confidence reduction reflects the lack of direct description, but the pattern established by sibling tools and the domain (PubMed literature search) makes misclassification unlikely.
From the tool's definition Tool name 'find_related' in context of PubMed/literature server strongly suggests retrieving related articles or citations; sibling tools (fetch_article, search_by_author, search_pubmed) are all read-only queries with no side effects.
Attacks that exploit this kind of access
find_related. It is categorised as a Read tool in the Ryogena Pubmed MCP Server, which means it retrieves data without modifying state.
Register the Ryogena Pubmed MCP server in PolicyLayer and add a rule for find_related: 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 Ryogena Pubmed. Nothing to install.
find_related 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 find_related 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 find_related. 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.
find_related is provided by the Ryogena Pubmed MCP server (kylevick4/pubmed-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 →