[DEV] Get MCP tool execution performance metrics.
AI agents call get_performance_metrics 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.
This tool retrieves performance metrics—a read-only operation with no side effects. The [DEV] annotation suggests it is a development/diagnostic utility. Retrieving metrics poses minimal security risk as it only queries existing operational data without modifying state, executing commands, or affecting other systems.
From the tool's definition Tool name 'get_performance_metrics' and description '[DEV] Get MCP tool execution performance metrics' indicate retrieval of metrics data with no data modification, deletion, or external execution.
Documented attack patterns abuse exactly the kind of access get_performance_metrics 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_performance_metrics:
{
"version": "1",
"default": "deny",
"tools": {
"get_performance_metrics": {}
}
}get_performance_metrics 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.
[DEV] Get MCP tool execution performance metrics. 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_performance_metrics: 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_performance_metrics 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_performance_metrics 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_performance_metrics. 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_performance_metrics 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.