The MCP server analytics give project owners and administrators visibility into how their knowledge base is being accessed through the Model Context Protocol (MCP) server. You can track call volumes, success and failure rates, tool usage, active users, MCP client distribution, and search activity - all in one dashboard. This helps you measure the value delivery of your MCP integration and understand how AI assistants and team members are interacting with your knowledge base.
Accessing the MCP server analytics page
To access the MCP server analytics, from the Knowledge base portal:
Navigate to Analytics () in the left navigation bar.
In the left navigation pane, click MCP server.
NOTE
Any team member with view analytics permission can access the dashboard.
Using filters to customize data
By default, the data shows metrics for the last week. You can adjust these using filters:
Click the Date filter dropdown.
Select a predefined range (Last week or Last month) or choose Custom date to specify a date range.
NOTE
The selected date range persists as you navigate across other analytics pages.
MCP server analytics page overview
The top of the dashboard displays four KPI cards summarizing activity for the selected period:
Metric | Description | How this helps |
|---|---|---|
Total calls | Total number of MCP calls made within the selected period | Whether MCP is actively being used after setup. If calls are lower than expected, check whether MCP assistants are connected correctly and whether users are aware that MCP access is available. |
Success rate | Percentage and count of successfully completed MCP calls | Whether connected MCP clients are able to retrieve or perform actions successfully. A drop in success rate can indicate authentication issues, permission restrictions, unavailable assist, or request failures from the connected client. |
Failure rate | Percentage and count of failed MCP calls | Whether MCP requests are repeatedly failing and need investigation. If failures are high, compare with the MCP tools operation chart to identify whether failures are concentrated in Read or Write operations, then review client configuration, access permissions, and rate limits. |
Active users | Number of unique users who made at least one MCP call in the selected period | Whether MCP usage is distributed across the team or limited to a few users. If total calls are high but active users are low, MCP may be used heavily by only a small group, which can help admins plan enablement or training. |
Charts
The Charts section helps you analyze MCP usage trends in more detail, including call volume, tool performance, user activity, client distribution, and search activity for the selected date range.
MCP call volume
Displays the day-by-day MCP call activity across all users. Hover over any point on the chart to see the total calls, success count, failure count, and success rate for that day. Click Export image () to save the chart as a PNG.
MCP tools operation
Shows the distribution of MCP calls broken down by operation type (Read and Write), with each bar segmented by success and failure counts. This helps you understand whether your MCP usage is primarily read-heavy (content retrieval) or write-heavy (content creation and editing), and how each operation type is performing. Click All, Success, or Failed to filter the chart view.
MCP tool calls by usage
Shows how frequently each MCP tool is called during the selected period, ranked by call volume. Use this chart to identify which tools are most frequently invoked and which are underutilized. Hover over any bar to see the total calls, success count, failure count, and success rate for that tool.
To learn more about each tool and what it does, read the article on Supported MCP tools.
Top users
Displays the top users ranked by MCP call volume for the selected period. The top 5 users are shown by default. Hover over any bar to see that user's total calls, success count, failure count, and success rate. Click View all to see the full list, where you can sort by call volume and search for a specific user.
Top MCP clients
Displays the top AI assistants connecting to your MCP server, ranked by call volume for the selected period. The top 5 assistants are shown by default. Hover over any bar to see the total calls, success count, failure count, and success rate for that client. Click View all to see the complete list.
MCP search tool
Displays the number of daily search queries made through the Search tool specifically. This is separate from the broader MCP tool calls. This chart helps you understand how frequently AI assistants are searching your knowledge base and whether search volume is growing over time.
NOTE
The MCP server analytics dashboard remains accessible even if MCP is disabled in your AI settings, as long as data is available for the selected date range. This helps you review past MCP activity without turning MCP back on.
For example, if MCP was enabled last month and later disabled, you can still select last month in the date filter and view the calls, users, clients, and tool usage recorded during that period.
FAQ
Why can I still see the MCP server analytics dashboard after disabling MCP?
The dashboard displays historical data regardless of whether MCP is currently enabled. Disabling MCP stops new data from being collected but does not remove existing analytics.
What are the reasons for the failure rate?
There are a few common reasons why MCP calls may fail:
Token limit exceeded (plan) - The AI assistant has hit its plan-level token limit, preventing further MCP tool calls.
Token limit exceeded (session) - The current session token limit is maxed out. Even if overall credits are available, a fully consumed session prevents further MCP tool calls until a new session is started.
Rate limiting - Too many requests are being made beyond what the plan allows.
Network interruption - A connectivity issue, such as an internet or Wi-Fi disruption mid-session, resulted in a failed call.