--- sourceDocument: Australia Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences Release : - australia ft:locale : - en-US ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Monitoring an MCP server # Monitoring an MCP server {#ariaid-title1} Release version: Australia Updated October 14, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Monitoring an MCP server This content explains how to monitor an MCP (Model Consumption Platform) server's tool performance using the Monitor tab on an MCP server record. It helps ServiceNow customers identify tools that fail frequently or respond slowly by reviewing key metrics such as request counts, success rates, and latency percentiles for each tool called by AI agents via AI Gateway. Unlike AI system monitoring, which focuses on quality and safety, this monitoring emphasizes operational performance of tools on the MCP server. Show full answer Show less ## Key Features * **Performance Metrics per Tool:** Displays the number of requests, success rate (percentage of successful HTTP responses), and latency percentiles (P50, P90, P95) that represent typical and worst-case response times over the last 30 days. * **Latency Percentiles Explained:** P50 shows median latency, P90 represents the threshold below which 90% of requests complete, and P95 indicates the slowest 5% of requests. These percentiles help distinguish between typical performance and occasional slow responses. * **Operational Focus:** The tab summarizes calls agents make to tools through AI Gateway, enabling users to track operational health without switching to the AI Gateway server-wide view. * **Managed Server Requirement:** Metrics appear only for managed MCP servers; unmanaged servers prompt a message to manage the asset before monitoring data is shown. ## Practical Application for ServiceNow Customers * Identify tools returning errors by comparing success rates alongside request volumes to understand the scope and impact of issues on AI agents. * Detect tools with slow response times by analyzing latency percentiles, especially focusing on the P95 value for worst-case scenarios that may delay workflows. * Prioritize investigation of tools that have both low success rates and high request counts, as these affect the greatest number of agent calls. * Review tools with acceptable success rates but significant latency variation (large gaps between P50 and P95) to address intermittent slow responses. This monitoring enables ServiceNow customers to proactively maintain MCP server tool performance, ensuring AI agents operate efficiently and reliably. Identify tools on an MCP server that fail often or respond slowly by reviewing request counts, success rates, and latency percentiles for each tool that AI agents call through AI Gateway. The Monitor tab on an MCP server record summarizes how each tool on that server performs when AI agents call it through AI Gateway. AI Gateway records the calls that agents make to the tools on the server, and the tab summarizes those calls for each tool. Unlike the Monitor tab for an AI system, which reports quality and safety scores, the Monitor tab for an MCP server reports operational performance. For metrics across all MCP servers, see . ## Key benefits {#mon-ai-mcp-server-monitor__key-benefits} * Find tools that return errors by comparing success rates across every tool on a server. * Judge how widely a problem affects agents by comparing each tool's success rate with its request count. * Detect slow responses by comparing median and worst-case latency for each tool. * Review tool performance on the MCP server record without switching to the AI Gateway view of all servers. {#mon-ai-mcp-server-monitor__ul_benefits} ## When tool metrics appear {#mon-ai-mcp-server-monitor__availability} Tool metrics appear for managed MCP servers. For an unmanaged server, the tab displays a message that the asset must be managed before the dashboard can appear. ## MCP tools observability metrics {#mon-ai-mcp-server-monitor__tool-metrics} The MCP tools observability metrics list shows one row for each tool that agents called during the last 30 days. The list contains the following columns. Tool name : Name of the tool as defined by the MCP server. Requests : Number of times agents called the tool during the period. Use this value to judge how much weight to give the other columns for the same tool, because a low success rate across many requests indicates a broader problem than the same rate across a few requests. Success rate : Percentage of the tool's requests that returned an HTTP status code from 200 through 299. A low value indicates that agents are receiving errors from the tool. Latency P50 : Request duration, in milliseconds, at or below which 50 percent of the tool's successful requests completed. This is the median, so it represents typical performance. Latency P90 : Request duration, in milliseconds, at or below which 90 percent of the tool's successful requests completed. The slowest 10 percent of successful requests took longer. Latency P95 : Request duration, in milliseconds, at or below which 95 percent of the tool's successful requests completed. The slowest 5 percent of successful requests took longer. {#mon-ai-mcp-server-monitor__dl_mcp_tool_columns} ## Reading latency percentiles {#mon-ai-mcp-server-monitor__latency-percentiles} Percentiles describe the spread of response times rather than a single average. Comparing the three latency values for the same tool shows whether slow responses are typical or occasional. When P50 is low but P90 and P95 are much higher, most calls respond quickly while a minority run slowly. For example, a tool with a P50 of 553 ms and a P95 of 1,845 ms responds in about half a second for a typical call, and roughly one successful call in 20 takes about 1.8 seconds or longer. P95 is the most useful of the three for judging worst-case behavior in workflows where one slow response delays the whole task. Latency percentiles are calculated from successful requests only. Requests that return an error count toward Requests and Success rate but not toward the latency columns, so a tool that fails often can still show low latency. A tool with no successful requests shows a latency of 0. Latency values are approximate, with a relative error of up to 1 percent. For a tool with few successful requests, the three values are often identical because each is calculated from the same small set of requests. Percentiles carry more meaning as the request count grows. ## Prioritizing tools to investigate {#mon-ai-mcp-server-monitor__prioritizing-tools} Tools that combine a low success rate with a high request count affect the most agent calls, so they are the strongest candidates for investigation. Tools with an acceptable success rate but a wide gap between P50 and P95 are candidates for a latency review.