ArcGIS MCP. Solve any location problem in 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.
ArcGIS MCP Server automates mapping and spatial analysis. Use it to perform geocoding, solve complex routes, and calculate service areas from any AI agent.
You can convert street addresses to coordinates, optimize vehicle routes for logistics, and figure out the closest address to any given latitude/longitude pair.
What your AI agents can do
Batch geocode addresses
Converts up to 1,000 addresses provided in an array into latitude and longitude coordinates.
Calculate od matrix
Calculates travel time and distances between a set of specified starting points and ending points.
Calculate service area
Determines the drive-time, walk-time, or travel-distance polygon reachable from a specified facility location.
It converts raw street addresses into precise latitude and longitude coordinates using geocoding.
It takes up to 1,000 addresses and converts them to coordinates in one go, saving time on bulk data entry.
It determines the most efficient driving path, providing turn-by-turn directions and total travel time for multiple points.
It solves Vehicle Routing Problems (VRP) to plan the most efficient sequence of stops for a whole fleet.
It calculates the geographical area (polygon) that is reachable from a single point within a specified time or distance.
It computes the travel time and cost matrices between a list of origins and a list of destinations.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
ArcGIS MCP Server: 10 Tools for Geospatial Analysis
These tools let your agent perform every major GIS calculation: geocoding, route solving, service area mapping, and VRP optimization.
019d7551batch geocode addresses
Converts up to 1,000 addresses provided in an array into latitude and longitude coordinates.
019d7551calculate od matrix
Calculates travel time and distances between a set of specified starting points and ending points.
019d7551calculate service area
Determines the drive-time, walk-time, or travel-distance polygon reachable from a specified facility location.
019d7551find address candidates
Suggests potential addresses or places using a text input to help users select a valid location before geocoding.
019d7551find address country
Finds an address and resolves coordinates, restricting the search only to a specific country.
019d7551reverse geocode
Converts a specific longitude/latitude coordinate pair into the closest known street address.
019d7551solve nav route
Finds the most efficient driving route between two or more locations, providing turn-by-turn directions and total travel time.
019d7551solve vehicle routing
Solves complex Vehicle Routing Problems (VRP) by optimizing the sequence of stops for a vehicle fleet.
019d7551suggest geocoding
Gives autocomplete suggestions for partial addresses or place names as the user types.
019d7551suggest location bias
Gets autocomplete suggestions for places that are biased towards a specific set of coordinates.
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 ArcGIS, 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
This server lets your AI client run complex mapping and spatial analysis directly. You'll use it to geocode addresses, figure out the best routes, and calculate service boundaries without leaving your current workflow. batch_geocode_addresses takes up to a thousand addresses and spits out their latitude and longitude coordinates all at once.
If you need to find coordinates from a raw street address, use find_address_candidates first to suggest potential locations, or use find_address_country if you only want to search within a specific country. To convert a specific longitude and latitude pair back into a street address, just call reverse_geocode. When you're ready to figure out the most efficient path, solve_nav_route finds the best driving route between two or more spots, giving you turn-by-turn directions and the total travel time.
For a whole fleet, solve_vehicle_routing solves complex Vehicle Routing Problems, optimizing the sequence of stops for all your vehicles. Need to know what area a facility covers? calculate_service_area determines the full polygon reachable from a single spot, whether you're measuring by drive time, walk time, or travel distance. Before you calculate anything, you might need to get suggestions for partial addresses using suggest_geocoding or get location suggestions biased toward specific coordinates with suggest_location_bias.
If you're mapping travel constraints, calculate_od_matrix computes the travel time and distance between a set of starting points and a set of ending points.
How ArcGIS MCP Works
- 1 Subscribe to the server and enter your ArcGIS Developer API Key.
- 2 Tell your AI agent what kind of spatial data you need (e.g., 'Calculate the optimal route from Point A to Point B').
- 3 The agent calls the appropriate tool, and you get the calculated coordinates, optimized route, or service area polygon back.
The bottom line is: you tell your AI agent what location problem you have, and it executes the complex GIS calculations for you.
Who Is ArcGIS MCP For?
The logistics manager tired of exporting data to Excel and running separate route optimization tools. The retail store planner who needs to map service boundaries for new locations. The real estate data scientist who needs to quickly validate and enrich property listings with hyper-local context. This is for anyone whose job depends on accurate location intelligence.
Optimizes multi-day fleet routes and calculates exact driving times between depots and delivery zones.
Runs batch address queries to validate and enrich property listings with accurate, geocoded coordinates.
Maps out service areas around current facilities to understand the full geographic reach of a business.
What Changes When You Connect
- Optimizes fleet routes with
solve_vehicle_routing. Instead of manually calculating optimal stop sequences, you give the AI agent the stops, and it returns the full, optimized plan for your entire fleet. - Handles massive data sets with
batch_geocode_addresses. You can process up to 1,000 addresses in one call, skipping the tedious step of running 1,000 individual geocoding queries. - Determines service boundaries with
calculate_service_area. You don't guess a facility's reach; you calculate the exact polygon of drive-time or walk-time coverage from that single point. - Finds the best path with
solve_nav_route. Give it multiple points, and you get a precise, turn-by-turn itinerary with total distance and travel time, skipping the need for external mapping tools. - Validates messy data with
find_address_candidates. Before running a full geocode, the agent uses this tool to suggest and correct ambiguous addresses, preventing bad data from polluting your calculations. - Compares multiple markets with
calculate_od_matrix. You can quickly determine travel cost and time between multiple origins and destinations, essential for multi-market planning.
Real-World Use Cases
Optimizing a Day's Deliveries
The logistics planner needs the most efficient route for 15 stops. They ask the agent to 'solve the vehicle routing for these stops.' The agent runs solve_vehicle_routing, returns the optimal sequence, and calculates the total mileage and time, solving the whole day's plan in one step.
Market Expansion Analysis
A retail business needs to see how far a new store can practically reach. They ask the agent to 'calculate the service area from this address.' The agent runs calculate_service_area and returns the exact polygon, letting the planner understand the true market boundary.
Cleaning Property Data
A data scientist has a spreadsheet of 500 addresses. They use the agent to run batch_geocode_addresses on the whole list. The agent returns a JSON array of coordinates, instantly cleaning and validating the entire dataset.
Calculating Cross-State Travel Costs
The operations lead needs to compare travel time between three warehouses in Texas and three in Louisiana. They ask the agent to 'calculate the OD matrix for these six points.' The agent runs calculate_od_matrix and provides a matrix of travel constraints, making comparisons instant.
The Tradeoffs
Using only basic geocoding
Trying to figure out the best route by running a simple geocode on all points and then guessing the order in Excel. This ignores travel time, traffic, and optimal sequencing.
→
First, use find_address_candidates to validate all addresses. Then, run solve_vehicle_routing to determine the optimal, sequenced path that minimizes total travel time.
Ignoring country constraints
Running a general address query for 'Main Street' and getting results from other countries, even though the business is only in the USA.
→
Always use find_address_country when searching for locations to guarantee the results are geographically bounded to your target country.
Manually stitching coordinates
Copying coordinates from one tool's output and pasting them into a second tool's input, risking formatting errors or missing data points.
→
Let the AI agent manage the flow. Pass the raw data to the agent, and it will sequence the necessary calls (e.g., batch_geocode_addresses followed by solve_nav_route) to handle the data handoff automatically.
When It Fits, When It Doesn't
Use this if your problem is inherently spatial—you need to know where things are or how to get from A to B. Specifically, if you need to optimize a sequence of stops (use solve_vehicle_routing), compare travel times between many points (use calculate_od_matrix), or map a reachable area (use calculate_service_area).
Don't use this if you simply need a single, one-off address lookup; use a simpler coordinate lookup tool instead. More importantly, don't use this if your problem is non-geospatial (e.g., 'write an email'). This tool is for location data only. It’s designed to handle the entire lifecycle of location intelligence, from raw address input to final optimized path.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ArcGIS. 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 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Mapping a service area shouldn't require a GIS specialist.
Traditionally, figuring out the true service area—the polygon of every location you can reach from your facility within a certain drive time—means opening a specialized GIS dashboard. You then manually set the distance radius, choose the travel mode (walk, drive), and run the calculation. This is a clunky, multi-step process requiring deep domain knowledge just to draw a boundary.
Now, you just tell your agent, 'What is the drive-time service area from this address?' The agent runs the `calculate_service_area` tool and returns the precise, ready-to-use polygon. You get the final map data without leaving your chat window.
ArcGIS MCP Server: Solve complex routing in one step
Before this, calculating a route that hits five stops optimally required multiple API calls: first, geocoding all five stops; second, calculating the travel matrix; and third, feeding the results into a specialized solver. It was a messy, sequential data handoff that often introduced errors.
Now, the agent handles the entire sequence. You give it the stops, and it uses `solve_vehicle_routing` or `solve_nav_route` to return the single, optimized solution. The data pipeline disappears.
Common Questions About ArcGIS MCP
How do I find the address closest to coordinates using reverse_geocode? +
Simply ask your agent to run reverse_geocode and provide the coordinates in the format 'lon,lat'. The agent returns the nearest street address, complete with the full address details.
Can I process a large list of addresses using batch_geocode_addresses? +
Yes. You provide the list of up to 1,000 addresses in a JSON array string, and the agent executes batch_geocode_addresses to return all coordinates at once.
What is the difference between solve_nav_route and solve_vehicle_routing? +
Use solve_nav_route for finding the best path between 2-5 stops. Use solve_vehicle_routing when you need to optimize the entire sequence of stops for a full fleet or multiple vehicles.
How do I find an address in a specific country using find_address_country? +
You tell the agent to use find_address_country, providing the address text and the country code (e.g., 'USA'). This ensures the search results are strictly limited to that geographical region.
How do I use `calculate_service_area` to determine the reach of a facility? +
You provide the facility's coordinates (lon,lat) and specify the calculation type (drive-time, walk-time, or travel-distance). The tool then calculates the polygon representing all locations reachable from that point within the specified travel constraint.
Can I suggest addresses before running a full geocode using `suggest_geocoding`? +
Yes, suggest_geocoding gives you autocomplete suggestions for partial addresses or place names. This helps narrow down potential results and ensures you select a valid address before committing to a full, paid geocoding request.
What is the input format required for `solve_vehicle_routing`? +
The input must be an ArcGIS Orders JSON mapping string. This detailed JSON structure needs to specify all required stops, the sequence, and any constraints for the entire fleet to solve the complex Vehicle Routing Problem.
How do I calculate travel constraints using `calculate_od_matrix`? +
You pass multiple origin and destination coordinate pairs to calculate_od_matrix. It returns a cost matrix detailing the travel time and distances between every single origin and destination point in your set.
Can my AI agent process a spreadsheet of hundreds of addresses into coordinates automatically? +
Yes. Simply share an array or JSON of addresses, and your agent can use the batch geocoding tool to process up to 1000 records in a single API call, returning precise latitude and longitude faster than any manual lookup.
How can I figure out the optimal driving route between 5 delivery stops? +
Share the coordinates of your multiple stops (lon,lat) with your AI agent. It utilizes the ArcGIS route solving engine to compute the fastest sequential path and returns a detailed breakdown of turn-by-turn directions and exact travel estimates.
Can I search for a location but strictly within a particular country? +
Absolutely. You can request the agent to geocode a place and pass a specific ISO country code (e.g., FRA for France, USA for United States). This ensures your spatial results are strictly bounded to that region, ideal for local datasets.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
LangGraph Cloud (Stateful AI Agents)
Orchestrate stateful AI agents via LangGraph Cloud — manage assistants, monitor conversation threads, and handle human-in-the-loop overrides.
Modal (Serverless AI Infrastructure)
Manage serverless compute via Modal — audit active apps, track GPU deployments, and monitor network volumes.
Google BigQuery
Empower your AI agent to query massive datasets via BigQuery — execute Standard SQL, track active jobs, and inspect table schemas natively.
You might also like
Dubsado
Run your creative business with proposal templates, contract signing, invoicing, and client scheduling in one seamless flow.
SingleStore
Equip your AI agent to natively interact with your SingleStore database. Execute raw SQL queries, perform semantic vector searches, list workspaces, and audit billing directly from the terminal.
Klevu (E-commerce AI Search)
Power your e-commerce discovery via Klevu AI — execute keyword searches, manage category merchandising, and retrieve product recommendations.