AI agents call get_pipeline_history to retrieve information from Pubmed Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name 'get_pipeline_history' follows standard read operation naming conventions (get/retrieve). In the context of a research assistant MCP server, this most likely retrieves metadata or logs about previous search/analysis pipelines without modifying state. The presence of a separate 'delete_pipeline' tool confirms that destructive operations are implemented separately.
From the tool's definition Tool named 'get_pipeline_history' with empty description; contextual clues suggest it retrieves historical data about pipelines in a research analysis system. The 'get' prefix strongly indicates a read-only retrieval operation.
Documented attack patterns abuse exactly the kind of access get_pipeline_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pubmed Search, and nothing reaches the server without passing your rules. This is the rule we recommend for get_pipeline_history:
{
"version": "1",
"default": "deny",
"tools": {
"get_pipeline_history": {}
}
}get_pipeline_history 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.
get_pipeline_history. It is categorised as a Read tool in the Pubmed Search MCP Server, which means it retrieves data without modifying state.
Register the Pubmed Search MCP server in PolicyLayer and add a rule for get_pipeline_history: 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 Search. Nothing to install.
get_pipeline_history 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 get_pipeline_history 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 get_pipeline_history. 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.
get_pipeline_history is provided by the Pubmed Search MCP server (u9401066/pubmed-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pubmed Search, 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.
63 Pubmed Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.