Run multi-source search and merge using the existing query plan.
AI agents call search_and_merge to retrieve information from Literature Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates biomedical literature data using a pre-existing query plan. It performs queries across multiple sources and consolidates results—classic read-only operations with no side effects, data modification, or destructive capability. The 'merge' operation combines search results rather than altering underlying data.
From the tool's definition Tool name and description indicate 'search' and 'merge' operations on literature sources. The server context describes 'literature search, open-access paper retrieval' as core functions.
Attacks that exploit this kind of access
Run multi-source search and merge using the existing query plan. It is categorised as a Read tool in the Literature Agent MCP Server, which means it retrieves data without modifying state.
Register the Literature Agent MCP server in PolicyLayer and add a rule for search_and_merge: 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 Literature Agent. Nothing to install.
search_and_merge 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 search_and_merge 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 search_and_merge. 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.
search_and_merge is provided by the Literature Agent MCP server (zouxy111/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 →