Check MCP performance metrics with objective benchmarks and optimization opportunities When to use: Monitor system health, identify bottlenecks, optimize workflows. This tool is for developers & system admins only. Only use when specifically asked for. Returns: Performance stats with benchmarks, ...
AI agents call get_mcp_performance to retrieve information from StockSpark MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves system performance metrics and benchmarks without creating, modifying, deleting, executing code, or initiating financial transactions. It is explicitly described as monitoring functionality for developers and system administrators only.
From the tool's definition Tool name 'get_mcp_performance' and description 'Check MCP performance metrics' indicate a retrieval operation that returns 'Performance stats with benchmarks, error rates, and specific recommendations' with no modification or side effects.
Attacks that exploit this kind of access
Check MCP performance metrics with objective benchmarks and optimization opportunities When to use: Monitor system health, identify bottlenecks, optimize workflows. This tool is for developers & system admins only. Only use when specifically asked for. Returns: Performance stats with benchmarks, error rates, and specific recommendations Benchmark context: API calls <1s (excellent), 1-2s (good), 2-5s (acceptable), >5s (needs optimization). It is categorised as a Read tool in the StockSpark MCP Server MCP Server, which means it retrieves data without modifying state.
Register the StockSpark MCP Server MCP server in PolicyLayer and add a rule for get_mcp_performance: 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 StockSpark MCP Server. Nothing to install.
get_mcp_performance 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_mcp_performance 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_mcp_performance. 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_mcp_performance is provided by the StockSpark MCP Server MCP server (loukach/stockspark-mcp-poc). 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 →