AI agents call build_search_pipeline to retrieve information from PubMed Advanced MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests constructing a search pipeline, which in the context of this PubMed server is most likely a read/query operation. However, the description is empty, so confidence is reduced. Sibling tools are all read-oriented (search, fetch, find), suggesting this tool is also read-focused. Severity is low as miscategorization at worst retrieves unintended literature data.
From the tool's definition Tool name 'build_search_pipeline' on a server described as providing tools for 'searching, retrieving, and linking biomedical literature from PubMed and PMC'
Documented attack patterns abuse exactly the kind of access build_search_pipeline gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PubMed Advanced MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for build_search_pipeline:
{
"version": "1",
"default": "deny",
"tools": {
"build_search_pipeline": {}
}
}build_search_pipeline 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.
build_search_pipeline. It is categorised as a Read tool in the PubMed Advanced MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PubMed Advanced MCP Server MCP server in PolicyLayer and add a rule for build_search_pipeline: 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 PubMed Advanced MCP Server. Nothing to install.
build_search_pipeline 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 build_search_pipeline 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 build_search_pipeline. 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.
build_search_pipeline is provided by the PubMed Advanced MCP Server MCP server (suyashekhande/pubmed-mcp-advanced). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PubMed Advanced 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.
16 PubMed Advanced MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.