CDC WONDER MCP. Pull structured public health data via conversation.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
query_wonder_database. Access the CDC WONDER system to pull structured public health data. This tool lets you query massive databases—including mortality, birth rates, and vaccine adverse events—using natural language through your AI agent.
Stop navigating complex web forms; just tell your agent what data you need, and it runs the query against the D76, D10, and VAERS databases.
What your AI agents can do
Query wonder database
Queries CDC WONDER epidemiologic databases by accepting a database ID and a JSON object of filtering parameters.
Pulls data from the D76 or D77 databases, allowing you to filter by year, region, and specific causes of death.
Queries the D10 Natality database to retrieve birth rates and maternal health statistics for specified locations.
Retrieves records from the VAERS database to monitor reported vaccine adverse events.
Executes highly specific, complex queries using standard CDC parameters (like B_, M_, V_ prefixes) to pinpoint exact data segments.
Pulls large, structured datasets suitable for immediate integration into other analytical software or models.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
CDC WONDER MCP Server: 1 Tool for Public Health Data
Use the `query_wonder_database` tool to query CDC WONDER databases, fetching structured data for mortality, births, and vaccine safety reports.
019e3874query wonder database
Queries CDC WONDER epidemiologic databases by accepting a database ID and a JSON object of filtering parameters.
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 CDC WONDER (Epidemiologic Data), 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
You'll use query_wonder_database to pull structured public health data straight from the CDC WONDER system. This tool lets your AI client query massive databases, including mortality, birth rates, and vaccine adverse events, just by giving it a database ID and a JSON object of filters. You don't gotta navigate complicated web forms or worry about API syntax; you just tell your agent what data you need, and it runs the query against the D76, D10, and VAERS databases.
Pulling Mortality Rates
You can query the D76 or D77 databases to get mortality rates. You'll filter results by year, region, and specific causes of death.
Analyzing Birth Demographics
Need to analyze birth rates or maternal health stats? You query the D10 Natality database for those metrics at specific locations.
Checking Vaccine Safety
To monitor reported vaccine adverse events, you retrieve records from the VAERS database.
Running Structured Queries
Your agent executes highly specific, complex queries using standard CDC parameters like B_, M_, and V_ to pinpoint exact data segments.
Extracting Raw Data
Pull large, structured datasets from the system, perfect for feeding into other analytical software or models.
How CDC WONDER MCP Works
- 1 Subscribe to the server and provide your necessary CDC WONDER API Access Token, if required by your proxy.
- 2 Instruct your AI agent to perform the required query (e.g., 'Get mortality rates for 2021 in California').
- 3 The agent runs the query through
query_wonder_databaseand returns the structured epidemiologic table.
The bottom line is, you ask for the public health data, and the server returns a structured table ready for analysis.
Who Is CDC WONDER MCP For?
Epidemiologists, public health officials, and data scientists need this. If your job involves tracking health trends, analyzing mortality patterns, or monitoring vaccine safety reports, this server replaces weeks of manual web form clicking with a single conversation. It pulls raw data directly into your workflow.
Uses the server to quickly pull mortality and birth statistics from D76 and D10 databases without navigating the complex WONDER web interface.
Monitors current health trends and vaccine safety reports (VAERS) directly through the agent to inform policy decisions.
Feeds structured JSON epidemiologic data into larger analytical workflows, bypassing manual data extraction and cleaning.
What Changes When You Connect
- Access mortality and birth statistics instantly. Instead of spending hours clicking through the WONDER web interface, you simply ask your agent for D76 or D10 data, and it runs the query.
- Monitor vaccine safety data (VAERS) without leaving your IDE. Your agent executes
query_wonder_databasewith the VAERS ID, summarizing reported adverse events and counts for you. - Stop wrestling with complex forms. The server handles advanced CDC parameter logic (like B_, M_, V_ prefixes), allowing you to focus on the research question, not the database schema.
- Streamline complex data gathering. You can fetch raw, structured JSON epidemiologic data—perfect for feeding into other analytical tools or custom models.
- Compare multiple datasets easily. Run simultaneous queries against D76 (Mortality) and D10 (Births) in one chat session to compare trends across different life stages.
- Save time on data preparation. The data comes back structured and ready. You skip the tedious manual copy-pasting and cleaning that usually follows these reports.
Real-World Use Cases
Comparing death rates across states
A researcher needs to compare mortality rates for 2021 vs 2022 in three different states. Instead of logging into WONDER and running three separate reports, they ask their agent to run a single query using query_wonder_database for the D76 database, specifying all three states and both years. The agent returns a single comparative table.
Analyzing birth rate shifts post-pandemic
A public health official wants to see how birth rates changed in California using the D10 database. They prompt their agent, and the system applies the necessary location filters (F_ prefixes) and retrieves the raw natality data, allowing for immediate trend analysis.
Investigating a vaccine safety signal
A safety monitor needs to check for adverse events related to a specific vaccine code. They prompt their agent to use query_wonder_database with the VAERS ID and the code, getting a summarized report of reported events and counts, which they can then use for immediate review.
Integrating data into a Python model
A data scientist needs to feed CDC data into a custom predictive model. They ask their agent to fetch structured JSON epidemiologic data via query_wonder_database using the D77 database. The output is clean, machine-readable JSON, ready for integration.
The Tradeoffs
Manually navigating WONDER web forms
The user spends 45 minutes clicking through multiple dropdown menus, selecting date ranges, and hitting 'submit' multiple times just to get a single dataset.
→
Tell your agent to use query_wonder_database. You provide the intent and the parameters in plain language, and the tool executes the complex query in seconds.
Guessing API parameters
The user reads the documentation and tries to guess the correct combination of prefixes (B_, M_, V_) or database IDs, often resulting in an error page or incomplete data.
→
Let your agent handle the query construction. You only need to know the data you want, and the server uses query_wonder_database to build the correct, validated query structure.
Copy-pasting raw CSV exports
The user downloads a CSV file, then has to manually copy-paste the data into Excel or a spreadsheet, often losing formatting or needing cleanup.
→ The server returns structured JSON or a formatted table directly in your chat window. The data is clean and immediately usable for analysis.
When It Fits, When It Doesn't
Use this server if your job requires pulling large, historical, or complex public health statistics (mortality, birth rates, vaccine safety). You need data from specific, regulated sources like the CDC WONDER system, and you want to avoid the overhead of manual form filling or learning specialized API syntax.
Don't use this if you only need general, real-time, or non-structured data (e.g., a list of today's headlines). For simple lookups, a general search tool is fine. If your data source is proprietary and not covered by CDC WONDER, you need a custom data connector or a different type of server. This tool is for structured, massive, public health record retrieval only.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CDC WONDER. 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 1 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Gathering official health stats usually means hours of clicking through web forms.
Right now, getting comprehensive public health data means navigating the CDC WONDER site. You select the database (D76, D10, etc.), pick a date range, then filter by state, cause of death, or age group. You hit 'submit,' wait, and then download a raw CSV. You repeat this process for every variable you care about—mortality, then births, then vaccine safety. It's a massive, tedious loop of form filling and manual data stitching.
With this MCP server, you skip the forms entirely. You just tell your agent, 'Show me mortality rates for 2021 in California.' The agent uses `query_wonder_database` to run the full, complex query in the background. You get the exact, structured table you need, right in your chat. Done.
CDC WONDER MCP Server: Querying complex data in a single prompt.
The manual steps that disappear are the initial database selection, the complex parameter mapping (like knowing which prefix means 'female' or 'under 5'), and the repetitive data consolidation. You don't have to switch between the CDC website, the documentation, and your spreadsheet.
It's immediate. You talk to your agent, and it executes the complex data retrieval. The difference is that you move from manual, multi-step data collection to single-prompt, automated data extraction.
Common Questions About CDC WONDER MCP
How do I use the query_wonder_database tool with different databases? +
You specify the database ID (D76, D10, or VAERS) in your prompt. The agent handles the ID and structures the necessary parameters for the query_wonder_database tool.
Can query_wonder_database handle filtering by age group? +
Yes, the tool supports filtering by age groups using the required CDC parameters, ensuring the mortality data is segmented exactly how you need it.
Is the data from query_wonder_database real-time? +
The data is pulled directly from the official CDC WONDER system, providing accurate, official epidemiologic records. It is not a simulated or generalized dataset.
What if I need to combine mortality and birth data? +
You can ask your agent to run sequential queries against both the D76 and D10 databases. You then combine the structured outputs in your workflow, using the tool for each distinct dataset pull.
How does the `query_wonder_database` tool handle different parameter prefixes like B_, M_, and V_? +
The tool requires you to pass a JSON object containing all necessary parameters. You specify the prefixes (B_, M_, V_, F_, O_) and their values in that JSON object for the query to work.
What happens if I use `query_wonder_database` with an invalid database ID or parameter? +
The tool will return an error message detailing the invalid ID or parameter structure. This lets you correct the input and resubmit a functional query.
Does `query_wonder_database` support querying multiple different CDC databases in one request? +
No, you must initiate separate calls for different databases (like D76 or D10). Each call uses the query_wonder_database tool with the specific database ID.
Is there a limit to how many records I can fetch using `query_wonder_database`? +
The tool's output is constrained by the underlying CDC WONDER API limits. We recommend running complex queries in batches to avoid hitting rate limits.
Which databases can I access using this server? +
You can query any database supported by the CDC WONDER API by providing its ID to the query_wonder_database tool. Common IDs include D76 (Detailed Mortality), D10 (Natality), and VAERS (Vaccine Adverse Event Reporting System).
How should I format the parameters for a query? +
Parameters should be provided as a JSON object using the standard CDC prefixes: B_ for by-variables, M_ for measures, V_ for values, F_ for filters, and O_ for other options. The query_wonder_database tool handles the XML conversion for you.
Do I need to include the 'accept_datause_restrictions' parameter? +
No. The query_wonder_database tool is designed to handle the data use restrictions agreement internally. You only need to provide the specific database ID and the analytical parameters for your search.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Musixmatch
Largest music lyrics database — search tracks, retrieve lyrics, and identify artists via AI.
Snapchat Ads
Equip your AI agent with direct access to Snapchat Ads — manage campaigns, track ad performance, and optimize spend without opening Snapchat Ads Manager.
Farmonaut
Access satellite agriculture data via Farmonaut — monitor crop health with NDVI, weather, soil moisture, crop advisory, and deforestation alerts from any AI agent.
You might also like
CleverTap
Manage customer engagement and analytics via CleverTap — track campaigns, monitor user segments, and audit event data directly from any AI agent.
MRPeasy
Manage manufacturing and inventory via MRPeasy — track customer orders, MOs, and stock items directly from your AI agent.
Epsilon3 Aerospace Operations
Equip your AI agent to manage operational procedures, track execution runs, and monitor telemetry via the Epsilon3 API.