Baidu Analytics MCP. Audit traffic, check visitor sources, and view page rankings.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Baidu Analytics MCP Server connects your AI agent directly to Baidu's dominant web traffic data. It lets you audit site performance, track visitors, and query metrics like Page Views (PV) and Unique Visitors (UV) in plain conversation.
You can get real-time stats, analyze daily trends, or check where your traffic is coming from, all without navigating the Baidu Tongji Dashboard.
What your AI agents can do
Get daily trend
Gets a summary of traffic performance across a specified date range.
Get geo distribution
Retrieves data showing where the site's visitors are located geographically.
Get page rankings
Retrieves a list of the top pages that receive the most visitor traffic.
The agent retrieves a list of all sites connected to the Baidu Analytics account, including their unique IDs.
The agent pulls immediate statistics, providing total Page Views (PV), Unique Visitors (UV), and the current number of online users.
The agent audits traffic trends and performance summaries across specified date ranges.
The agent retrieves where visitors are located and how they arrived at the site (e.g., search, direct).
The agent pulls data on the pages that receive the most traffic and are ranked highest.
The agent runs advanced, custom queries against the site data using specific metrics.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Baidu Analytics MCP Server: 8 Tools for Site Metrics
Use these tools to audit daily traffic trends, segment visitor geography, and query specific site performance metrics via natural language commands.
019d841aget daily trend
Gets a summary of traffic performance across a specified date range.
019d841aget geo distribution
Retrieves data showing where the site's visitors are located geographically.
019d841aget page rankings
Retrieves a list of the top pages that receive the most visitor traffic.
019d841aget realtime metrics
Fetches the current, live statistics on visitor activity for the site.
019d841aget source data
Gathers details about the sources that drive traffic to the site (e.g., search, direct, referral).
019d841aget yesterday overview
Pulls a complete summary of the site's traffic performance from the previous day.
019d841alist sites
Lists every unique site ID and name registered within the Baidu Analytics account.
019d841aquery custom metrics
Runs advanced queries to calculate specific, custom metrics not covered by standard reports.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Baidu Analytics / 百度统计, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Baidu Analytics MCP Server connects your AI agent straight to Baidu's web traffic data. You'll use it to audit site performance, track visitors, and query metrics like Page Views (PV) and Unique Visitors (UV) just by talking to your agent. You never gotta mess with the Baidu Tongji Dashboard again.
list_sites lets your agent pull a list of every site ID and name registered in the Baidu Analytics account. get_realtime_metrics pulls the current, live stats for the site, giving you total Page Views (PV), Unique Visitors (UV), and the current number of online users. get_yesterday_overview provides a full summary of the site's traffic performance from the previous day. get_daily_trend lets you audit traffic performance summaries across any date range you specify. get_geo_distribution retrieves where your site's visitors are located geographically. get_source_data gathers details about the sources that drive traffic to the site, like search, direct, or referral. get_page_rankings pulls a list of the top pages that get the most visitor traffic. query_custom_metrics runs advanced queries to calculate specific metrics not covered by standard reports.
How Baidu Analytics MCP Works
- 1 Subscribe to the server and provide your Baidu Analytics credentials (Username, Password, Token, Site ID).
- 2 Ask your agent to perform a task (e.g., 'Show me the UV trend for last week').
- 3 The agent calls the necessary tool, processes the data, and returns the specific metrics in a readable format.
The bottom line is, your AI client acts as a data coordinator, running the necessary checks against Baidu's metrics and spitting out the answer.
Who Is Baidu Analytics MCP For?
This is for the digital marketer who spends hours clicking through dashboards. It's for the product manager who needs to know if a recent UI change tanked conversions. It's for the developer who needs to hook professional web analytics into a script without writing complex API calls. Basically, anyone whose job involves asking 'Why did traffic dip yesterday?'
Uses get_source_data to figure out which campaigns are underperforming and runs get_daily_trend to report weekly performance to leadership.
Uses get_page_rankings to see if new features are driving traffic to the right pages, and get_realtime_metrics to check immediate impact.
Uses get_geo_distribution to target specific regions and runs get_source_data to audit ranking sources.
What Changes When You Connect
- See real-time activity with
get_realtime_metrics. You get immediate metrics—Page Views (PV), Unique Visitors (UV), and current user counts—so you don't have to refresh a dashboard every five minutes. - Pinpoint traffic dips with
get_daily_trendorget_yesterday_overview. These tools give you historical context, showing if a drop was a one-off event or a sustained problem over weeks. - Target campaigns by source.
get_source_datatells you exactly if the traffic came from Google search, a specific social link, or a direct visit, letting you prove ROI. - Understand where your users are.
get_geo_distributionmaps your audience by region, letting you focus marketing efforts only on the countries or states that matter. - Know your winners. Use
get_page_rankingsto identify the pages driving the most engagement. This cuts through the noise and tells you where to build next. - Run deep custom reports.
query_custom_metricsallows you to bypass standard reporting limitations, giving you granular data points for complex hypotheses.
Real-World Use Cases
Checking performance right now
A product manager needs to know if the new checkout button is working. They ask their agent, 'What are the real-time metrics for my site?' The agent calls get_realtime_metrics and reports back the current UV and PV counts, letting the PM know if the launch was a success right now.
Debugging a sudden drop in traffic
The marketing team sees a big dip yesterday. They ask the agent to run get_yesterday_overview to set the baseline, then call get_daily_trend to see if the dip was limited to one day. Finally, they use get_source_data to narrow down if the drop came from a specific channel.
Identifying a key market
A global SEO specialist wants to focus on a new region. They ask the agent to use get_geo_distribution. The agent returns a map breakdown, showing the specialist exactly which cities or provinces need a targeted content strategy.
Comparing different site versions
A developer needs to compare two landing pages. They first use list_sites to confirm the IDs for both sites. Then, they use get_page_rankings for each ID to see which page is performing better and where users are actually clicking.
The Tradeoffs
Asking for everything at once
Asking the agent to 'Give me all the data: trends, geo, sources, and rankings.' This forces the agent to try and execute every tool, resulting in a massive data dump that's impossible to read and often times out.
→
Start with a clear question. For example, 'Show me the daily trend, and then break down the sources for the last week.' This sequence uses get_daily_trend followed by get_source_data to build a focused narrative.
Ignoring the timeline
Assuming that current metrics (get_realtime_metrics) tell you about long-term strategy. The real-time data is useless for budgeting or quarterly planning because it only captures the moment.
→
Always anchor your analysis in historical data. Use get_yesterday_overview or get_daily_trend first. Then, use get_realtime_metrics only to confirm the current state.
Using the wrong scope
Trying to query performance for a site that hasn't been registered. The agent will fail because the scope is wrong, wasting time and effort.
→
Always run list_sites first. This confirms the correct site ID, ensuring that subsequent calls like get_page_rankings or get_source_data target the right data set.
When It Fits, When It Doesn't
Use this if you need to answer specific questions about performance (e.g., 'Why did UV drop last Tuesday?' or 'Are users from Region X spending more time on Page Y?'). It is best for structured, investigative reporting. Don't use this if you just need a general idea of 'how the site is doing'—you'll get a massive, unstructured data dump. If you need to correlate data across unrelated domains (e.g., linking web traffic to ad spend in a separate CRM), use a general-purpose data pipeline tool instead. This server excels at deep, authoritative site data retrieval.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Baidu Analytics / 百度统计. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually compiling web traffic reports is a pain.
Today, you open the Baidu Tongji Dashboard. You have to click tabs for traffic trends, then drill down into source data. You copy the UV numbers into a spreadsheet, then you have to manually cross-reference page rankings against geographic data. It's a half-day of clicking, copying, and praying you don't miss a metric.
With the Baidu Analytics MCP Server, you just ask your agent. You ask, 'What was the UV trend last week, and where did they come from?' The agent runs `get_daily_trend` and `get_source_data` and hands you the complete answer in one go.
Baidu Analytics MCP Server: Get the full picture.
You no longer need to check five different reports to understand a single issue. You can ask the agent to run `get_realtime_metrics` to see the immediate impact, and then immediately follow up by calling `get_page_rankings` to see which page is getting hit hardest by the sudden spike.
It's not just about reading data. It's about coordinating the data sources. The agent makes the data flow. You get accurate, actionable results without ever leaving your chat window.
Common Questions About Baidu Analytics MCP
How do I use the `get_realtime_metrics` tool with Baidu Analytics? +
You simply ask your agent to 'Show me the real-time visitor stats.' The agent calls get_realtime_metrics and returns live counts for Page Views (PV), Unique Visitors (UV), and current online users.
Can I get historical data using `get_daily_trend`? +
Yes. You prompt the agent with a date range (e.g., 'What was the traffic trend for the last 30 days?'). The agent executes get_daily_trend and provides the necessary historical data points.
Which tool should I use to find out where my visitors are from? Use `get_geo_distribution`? +
That's right. Ask the agent to run get_geo_distribution. It returns a breakdown of your audience by geographic region, helping you target marketing efforts.
How do I run a custom report using `query_custom_metrics`? +
You must tell the agent exactly what you want. For example, 'Run a custom query for UV filtered by source type X.' This ensures the agent executes the specific API call you need.
Does `get_source_data` cover all traffic types? +
It covers the primary sources: search, direct, and referrals. Asking the agent to get the source data tells you which channels are driving your traffic, allowing for better campaign investment.
How do I list all the sites I need to track using the `list_sites` tool? +
You use list_sites to get a full list of every site connected to your account. This helps you verify all registered Site IDs before running any other reports.
What if I need to check the performance of yesterday's traffic, and should I use `get_yesterday_overview`? +
Yes, get_yesterday_overview gives you a quick summary of the previous day's performance. It's ideal for daily audits without needing to specify exact date ranges.
Can I check top-performing pages using the `get_page_rankings` tool? +
The get_page_rankings tool shows you the top visited pages on your site. This is useful for identifying content that drives the most user engagement.
How do I find my Baidu Analytics Token and Site ID? +
Log in to the Baidu Analytics Console, navigate to [Management] -> [Site List] to find your numeric Site ID. The API Token is usually provided in the API settings or developer services section after account verification.
What metrics are supported in real-time queries? +
Real-time tools provide access to Page Views (PV), Unique Visitors (UV), IP counts, and the current number of online users on your site.
Can I query data for specific dates? +
Yes! Use the trend and metric tools with start_date and end_date in YYYYMMDD format. Your agent will retrieve the historical data for the requested period.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Conductor (Netflix OSS)
Automate workflow orchestration via Netflix Conductor — manage workflow and task definitions, and start executions directly from any AI agent.
QRCodeChimp
Generate branded QR codes with tracking, analytics, and dynamic content that update without reprinting for any use case.
RenderForm
Generate dynamic images and social media graphics from templates with an API that personalizes visuals at scale for any campaign.
You might also like
Lunatask
Manage tasks, habits, and notes via the Lunatask REST API (Encrypted Metadata Only).
LocalAI
Run LLMs, generate images, and process audio locally. OpenAI-compatible API for your own hardware.
ClickHouse (Vector Search)
Manage vector embeddings and SQL via ClickHouse — list databases, execute SQL, and perform high-speed vector searches directly from any AI agent.