Supercharge your AI with TIGER/Line Geocoder (Census). Map any US address or coordinate to census boundaries.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
TIGER/Line Geocoder (Census) converts addresses and coordinates into precise, structured geographic data from the official US Census Bureau. It handles single-line lookups, full address resolution, Puerto Rico addresses, reverse geocoding of points to census boundaries, and batch processing for up to 10,000 records.
What your AI can do
Batch geocode address
Processes up to 10,000 rows of structured addresses from a CSV file into coordinates.
Batch geocode coordinates
Takes up to 10,000 coordinate pairs from a CSV and looks up their corresponding census geographies.
List benchmarks
Retrieves the list of available Census Geocoder benchmarks and their unique IDs.
Converts full, structured addresses into precise latitude and longitude pairs using geocode_address.
Takes a raw, single-line address string and returns its coordinates via the geocode_oneline tool.
Inputs Lat/Long points to determine which census tract or administrative block they belong to using geocode_coordinates.
Uses specialized logic (geocode_address_pr) to correctly geocode addresses within the Commonwealth of Puerto Rico.
Takes CSV data (up to 10,000 rows) containing multiple structured addresses and returns a batch set of coordinates using batch_geocode_address.
Checks which historical or current census benchmarks and vintages are available for querying via list_benchmarks and list_vintages.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 Compatible Gemini Waiting for input…
TIGER/Line Geocoder (Census): 8 Tools for US Mapping
These tools let you convert addresses to coordinates, perform reverse lookups on census boundaries, and process large datasets using the official US Census Bureau API.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using TIGER/Line Geocoder (Census) on VinkiusBatch Geocode Address
Processes up to 10,000 rows of structured addresses from a CSV file into coordinates.
Batch Geocode Coordinates
Takes up to 10,000 coordinate pairs from a CSV and looks up their corresponding...
List Benchmarks
Retrieves the list of available Census Geocoder benchmarks and their unique IDs.
Geocode Address Pr
Geocodes a full street address specific to Puerto Rico, respecting local parameters.
Geocode Address
Converts a single structured address input (street, city, state, zip) into...
Geocode Coordinates
Looks up the census geographies associated with a given latitude and longitude point.
Geocode Oneline
Converts a raw, single-line address string into coordinates.
List Vintages
Lists all specific data vintages associated with a chosen benchmark for use in...
Connect to your AI in seconds. Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token from
cloud.vinkius.com. For OAuth-protected servers, expand Advanced
settings to add credentials.
Start a conversation
Open a new chat. The TIGER/Line Geocoder (Census) integration is available immediately — no restart needed.
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 TIGER/Line Geocoder (Census), then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ 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
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by US Census Bureau. 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 connection provides 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Mapping an Address shouldn't require three different lookups.
Right now, if your dataset is mixed—some rows have full addresses (Street/City/State), and others are just raw text strings—you end up running multiple scripts. You might try a structured lookup, only to find the data source was messy, requiring you to write custom pre-processing steps just to format the input correctly.
With this MCP server, you get dedicated tools for both formats. Use `geocode_address` for clean inputs and `geocode_oneline` for raw text. Your agent handles the switch automatically, giving you a single JSON output with coordinates regardless of how messy the initial address data was.
TIGER/Line Geocoder (Census) MCP Server: Get Census Data in 4 Clicks
Before, finding out what kind of census block a point was on required multiple API calls—one for the coordinates, another to validate the vintage, and then potentially a third one just for the tract boundary. It's tedious, slow, and hard to manage in code.
Now, you call `geocode_coordinates` and get it all in one go. The agent handles the lookup against the correct census benchmark automatically. You get the definitive boundaries instantly.
What your AI can actually do with this
This server hooks your AI client directly into the US Census Bureau's TIGER/Line API. It takes raw location data—whether you got a clean street address or just some random latitude and longitude—and turns it into structured, verifiable geographic records from the official census. You don't have to manage any API keys or worry about complex setup; your agent just calls the tool.
If you need coordinates from a fully structured US address (street, city, state, zip), use geocode_address. That function handles standard inputs and spits out precise latitude and longitude pairs. When you've got a raw, single-line address string—like something pulled straight off a messy database entry—use the geocode_oneline tool; it figures out the coordinates from that mess.
Need to process thousands of records at once? You can handle huge data sets by uploading CSV files. If your file has multiple structured addresses, pass it through batch_geocode_address, and it'll return a batch set of corresponding coordinates for every row up to 10,000 entries. If you already have the coordinate pairs but need to know what census geography they belong to, use batch_geocode_coordinates on your CSV; that handles up to 10,000 pairs.
For reverse lookups—that is, when you only have a point of coordinates and wanna know which census tract or administrative block it falls into—you call geocode_coordinates, feeding it the latitude and longitude pair. For addresses in Puerto Rico specifically, don't use the general tool; you gotta run it through geocode_address_pr.
That specialized function uses its own logic to correctly geocode full street addresses within the Commonwealth.
When you're dealing with historical or time-sensitive data, you need to know what versions of census information are available. To see every current and past benchmark ID that the Census Geocoder supports, run list_benchmarks. Once you pick a specific benchmark, you call list_vintages to get all the unique, date-specific data vintages associated with it for your queries.
019e38fb-6ef2-7214-85a5-1da043cd7d3b 
Here's how it actually works
The bottom line is: you pass raw location text or numbers, and the server gives you verified, actionable geographic data that tells you exactly what type of area it is.
Tell your AI client exactly what you need to convert (e.g., 'Geocode 1600 Pennsylvania Ave NW').
The agent determines the correct tool and calls it, supplying the necessary data points like addresses or coordinates.
You get back structured JSON containing the precise longitude, latitude, and detailed census geography boundaries.
Who is this actually for?
Data Scientists who map demographic shifts need this. Urban Planners building infrastructure models rely on precise boundary data. Logistics managers needing to validate US shipping points also use it. If your job involves linking a physical location to official census stats, you need this.
Runs demographic analyses by mapping thousands of addresses to specific census tracts for cohort studies.
Identifies administrative boundaries and census blocks when planning new infrastructure or zoning changes in a region.
Validates incoming manifest addresses against official US data to normalize geographic points for routing and delivery tracking.
What Changes When You Connect
Stop dealing with vague location data. Use geocode_address or geocode_oneline to turn simple text into verifiable latitude/longitude pairs, giving you a concrete starting point for analysis.
Scale your process without breaking it. If you've got 5,000 addresses in a spreadsheet, use batch_geocode_address. It handles the volume so your agent doesn't choke on large data sets.
Know exactly what area you're looking at. Run reverse geocoding with geocode_coordinates to find the precise census tract and block boundaries for any given coordinate point.
Handle special cases correctly. If your work touches Puerto Rico, don't guess—call geocode_address_pr. It uses specialized logic for local parameters.
Maintain data integrity over time. Use list_benchmarks and list_vintages to ensure you are running your queries against the correct historical or current census dataset.
Simplify complex lookups. By centralizing this service, your agent knows whether it needs a single-line lookup (geocode_oneline) versus a full structured address (the core geocode_address), cutting down on logic errors.
See it in action
Validating Delivery Routes for New Warehouses
A logistics team needs to confirm 50 potential new warehouse sites. Instead of manually verifying every address, they run a CSV through batch_geocode_address. The server returns coordinates and confirms the exact census block, allowing them to calculate final routing costs immediately.
Analyzing Demographic Shifts Post-Event
A researcher needs to know which population groups were affected by a recent policy change. They take a list of known incident coordinates and run geocode_coordinates. The tool maps those points back to specific census tracts, allowing the agent to pull targeted demographic data for analysis.
Data Cleaning from Web Scrapes
A marketing team scrapes thousands of user-provided addresses but they are inconsistent. They run geocode_oneline on a sample batch. This validates the raw input, forcing it into standardized Lat/Long pairs and ensuring data quality before feeding it into their main database.
Comparing Data Across Time Periods
A city planner needs to compare infrastructure density from 2010 versus today. They use list_benchmarks first, select the correct historical vintage (e.g., Census2010), and then run targeted lookups, guaranteeing data consistency across decades.
The honest tradeoffs
Treating all addresses equally
Using geocode_address for a raw address string like 'Near the main street' and expecting results. It only works with structured inputs.
If you have an unstructured, single-line input, use geocode_oneline. If you have Street/City/State/Zip, stick to geocode_address for guaranteed structure.
Ignoring batch limits
Trying to upload 15,000 records into a single CSV file using the general geocoding tools. The process will fail or time out.
The server supports large-scale data with batch_geocode_address and batch_geocode_coordinates. Make sure your dataset is under the 10,000 row limit for reliable processing.
Mixing up coordinates vs. addresses
Trying to run a reverse lookup (finding the census tract) using geocode_address, which expects structured text input.
Use geocode_coordinates. You must pass valid Longitude and Latitude values, not an address string.
When It Fits, When It Doesn't
You use this server when your primary goal is verifiable location resolution tied to US census boundaries. Don't use it if you just need general mapping or basic geo-lookups; those might be handled by commercial map APIs. Use geocode_address if the input data has distinct fields (Street, City, State). Use geocode_oneline if your source material is messy and only provides one string per address. If you are analyzing huge datasets, always prioritize the batch tools (batch_geocode_*). Never assume current data; always check list_benchmarks first to confirm which census vintage you need.
Questions you might have
Can I get census tract and block information from a single address string? +
Yes! Use the geocode_oneline tool with returntype set to 'geographies'. Provide the address and a benchmark (like 'Public_AR_Current') to receive full geographic metadata.
How do I find out which census area a specific GPS coordinate belongs to? +
Use the geocode_coordinates tool. Input the longitude (x) and latitude (y) along with a benchmark and vintage. The agent will return the specific census layers for that point.
Does this server support geocoding for addresses in Puerto Rico? +
Yes, specifically via the geocode_address_pr tool. It includes fields for 'urb' (Urbanization) and 'municipio' which are essential for accurate Puerto Rico address matching.
How do I ensure data consistency when using the 'list_benchmarks' tool? +
You must always use list_benchmarks first to see what versions are available. The resulting benchmark IDs dictate which historical or current census data set your query runs against, preventing mismatch errors.
What is the maximum volume I can process using the 'batch_geocode_address' tool? +
The service supports batch processing for up to 10,000 addresses in a single run. This capacity handles large-scale data cleanup and analysis without requiring multiple separate API calls.
Can the 'geocode_oneline' tool handle incomplete or poorly formatted address strings? +
It requires a reasonably complete, single-line format to work. If the string is too vague (e.g., just a neighborhood name), the tool will return an error because it needs enough data points for mapping.
If I use 'geocode_address' and one address fails, does the entire batch process fail? +
No, failure in one record won't stop the whole job. The service processes records individually; it will return a status code or error message specifically for the failing address while continuing with the rest of your list.
Does 'geocode_coordinates' provide coverage outside of US Census Bureau data? +
No, this server is exclusively built on the official US Census Bureau TIGER/Line geocoding service. It provides accurate coordinates and census geographies only for locations within the United States.
We've already built the connector for TIGER/Line Geocoder (Census). Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.