Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Stadia Maps Location API MCP Server what time is it in Tokyo right now?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This is a Model Context Protocol (MCP) server that provides AI assistants with access to Stadia Maps APIs for location services, geocoding, routing, and mapping capabilities.
Time information anywhere on earth
Current time
Time zone info (ID, UTC offset, and whether a special offset like daylight saving/summer time is in effect)
Geocoding
Address lookup
Place search (POIs like restaurants, cafes, etc.)
Static map image generation (including markers and route overlays)
Routing & travel time
Isochrones (reachable range; both time and distance contours)
Here are just a few of the ways you can prompt an LLM to make use of the tools:
"What time is it in Tokyo?"
"Make me a map showing the walking route from Depoo Turg to the Põhjala Tap Room."
"Is the Põhjala Tap Room open right now? Use Stadia Maps to get this information."
"Geocode the addresses in the attached spreadsheet."
Related MCP server: OpenStreetMap MCP Server
We'll use bun for all of our instructions,
but you can use npm too.
Run bun install to fetch the dependencies.
Then, execute the build script: bun run build.
The built code should be in the build directory now.
This MCP server requires a Stadia Maps API key.
Follow the directions here to get your free key.
Then, set the API_KEY environment variable when running the server.
API key in hand, here are a few ways you can use the MCP server.
See Claude Desktop Setup for detailed instructions on configuring this MCP server with Claude Desktop. Claude Desktop is a great tool for testing out workflows.
See Warp Setup for detailed instructions on setting up Warp with this MCP server. Warp is a powerful agentic environment that uses LLMs to do things on your behalf. Whereas you would need to upload a file to Claude, Warp can directly access files, write code, and execute programs on your computer.
Paired with the Stadia Maps MCP, it's a powerful tool for tasks like bulk geocoding, spatially filtering datasets, and more.
For developers who want to integrate the MCP server programmatically into their TypeScript applications, we have an Anthropic SDK Integration Example. This example demonstrates how to:
Connect to the MCP server from your code
Integrate with Claude's API for natural language queries
Enhance Claude with spatial intelligence using the Stadia Maps APIs via an MCP server
LLMs are far from perfect, and sometimes you need to put some thought into crafting prompts to get good results.
Sometimes the model needs a nudge to use the right tool. For example, if you ask for opening hours, many models will try to search the web. This information isn't always easily available for the model to find online.
For example, watch what a model does here:
You can nudge the model to use the tools in this MCP like so:
LLMs are capable of a lot, but they can't always do everything. As an example, let's look at one way to bulk geocode addresses in a spreadsheet.
First, attach an Excel sheet in Claude Desktop which has a few addresses in a column.
Prompt: Geocode all the addresses in this spreadsheet. Add the geocoded latitude and longitude as new columns in the sheet.
At the time of this writing, Claude cannot generate a spreadsheet attachment directly, but it can generate an HTML page or other code which generates it for you! In fact, Claude Desktop may actually ask you if you want an Excel sheet download, but it will just go ahead and generate this for you instead.
This sort of creativity is necessary, particularly when interacting with current generation LLMs through the usual user interfaces. A lot of the power of MCPs is that you can interact with them through code, which can overcome some of these limitations to provide a delightful user experience.
Just like a human, LLMs do better when given the right tools for the job. And just like a master craftsman, you'll probably need some expert knowledge to know how best to combine the right tools and materials.
Additionally, models have a context limit. While there are advanced techniques to squeeze more out of this, you can only benefit by tailoring the MCP to the specific API functionality you need. Not to mention, it will be much cheaper for you to operate with just the tools you need for a specific context. Tool schemas are vast majority of the context cost, in a simple demo! If you build the suite out to ~10 tools, you can end up with tens of thousands of input tokens.
This project is a starting point,
and we've left comments throughout index.ts noting our approach to building tools,
and how you can tailor them for your use case.
Perform multiple address geocoding operations in a single request. Returns results as a JSON list, showing only the first result for each. Using this to geocode POIs is strongly discouraged, as many places with the same name exist; only use this for addresses. Returned geographic information includes coordinates, bounding box, local context (what country, city, etc. is it in).
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | Array of geocoding items to process in bulk. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it's a batch operation, returns only first result per query, includes what geographic information is returned (coordinates, bounding box, local context), and warns about limitations with POIs. It doesn't mention rate limits, authentication needs, or error handling, which keeps it from a perfect score.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured with three sentences that each earn their place: first states the core functionality, second provides critical usage guidance, third details return values. No wasted words, and the most important information (bulk geocoding for addresses only) is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description does well by explaining the batch nature, return format, and content of results. It could be more complete by mentioning error handling for invalid addresses or whether all items must succeed for the batch to complete, but it covers the essential context given the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description doesn't add any parameter-specific information beyond what's already documented in the schema. It focuses on overall tool behavior rather than explaining individual parameters like 'items', 'countryFilter', or 'layer'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('perform multiple address geocoding operations in a single request') and distinguishes it from the sibling 'geocode' tool by emphasizing bulk processing. It explicitly identifies the resource being operated on (addresses) and the output format (JSON list).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool ('only use this for addresses') versus when not to ('strongly discouraged' for POIs), and explains why (many places with same name exist). It also implies an alternative approach for POIs (using general knowledge or multiple queries), though it doesn't name specific sibling tools as alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up a street address, POI, or area. Returned geographic information includes coordinates, bounding box, local context (what country, city, etc. is it in).. Additional info may include Wikipedia ID, population, opening hours, website, and more, subject to availability.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The address or place name to search for. Use local formatting and order when possible. When searching for a POI name (e.g. 'Starbucks'), you will get better results with a focus point and filters. Avoid spelling out precise locations (e.g. 'Starbucks, Downtown Greenville'); this is acceptable for large areas though (e.g. 'Paris, France' is OK, as is 'Louvre, Paris'). Make multiple queries or use general knowledge when necessary to identify the correct non-textual filters. | |
| countryFilter | No | ||
| lang | Yes | A BCP-47 language tag (may just be the language) to localize the results in (e.g. en, de, et). | |
| focusPoint | No | Geographic coordinates to focus the search around. Provide this whenever possible. | |
| layer | No | The layer to search in. Coarse searches for areas such as neighborhoods, cities, states, and countries, AND a specific layer is not available. Address searches for street addresses. Country is what you expect. Localities are what we would colloquially refer to as a 'city', town, or village. Region is for first-level subdivisions within countries like states, provinces, or whatever they are called locally. POI searches for points of interest including restaurants, parks, shops, and museums. Defaults to all layers if not specified. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what the tool returns (coordinates, bounding box, local context, and additional info like Wikipedia ID) and mentions that information is 'subject to availability,' which adds useful context about potential variability. However, it doesn't cover important behavioral aspects like rate limits, authentication needs, error conditions, or whether it's a read-only operation (though 'look up' implies non-destructive).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded: the first sentence states the core purpose and return values, and the second sentence adds supplementary information about additional data. Every sentence earns its place with no wasted words, making it efficient and easy to understand.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (5 parameters, nested objects, no output schema), the description is reasonably complete. It explains what the tool does and what information it returns, which is adequate for a geocoding function. However, without annotations or an output schema, it could benefit from more detail about the structure of returned data or error handling, though the high schema coverage helps compensate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 80%, which is high, so the baseline is 3 even though the description doesn't add parameter-specific information. The description mentions the types of queries (street address, POI, area) which aligns with the 'query' parameter, but doesn't provide additional semantic context beyond what's already documented in the detailed schema descriptions for each parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('look up') and resources ('street address, POI, or area'), and distinguishes it from siblings by focusing on single-location geocoding (vs. bulk-geocode for multiple locations). It explicitly lists the types of information returned, making the function unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (for looking up addresses, POIs, or areas to get geographic information), but doesn't explicitly mention when not to use it or name alternatives. It implies usage for single queries rather than bulk operations, which differentiates it from 'bulk-geocode', but lacks explicit exclusions or comparisons to other siblings like 'isochrone' or 'route-overview'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate isochrone contours showing areas reachable within specified time or distance constraints from a single location. Returns GeoJSON polygons representing the reachable areas.
| Name | Required | Description | Default |
|---|---|---|---|
| location | Yes | A geographic coordinate pair. | |
| costing | Yes | The method of travel to use for isochrone calculation (auto = automobile). | |
| contours | Yes | Array of 1-4 contours. All contours must be of the same type (all time or all distance). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool 'Returns GeoJSON polygons representing the reachable areas,' which covers the output format. However, it lacks critical behavioral details: whether this is a read-only operation, computational cost, rate limits, authentication requirements, or what happens with invalid inputs. For a geospatial computation tool with no annotation coverage, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise with two sentences that each earn their place: the first defines the tool's purpose and scope, the second specifies the return format. It's front-loaded with the core functionality and contains zero redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (geospatial computation with multiple parameters and nested objects) and 100% schema coverage but no annotations or output schema, the description is minimally adequate. It covers the basic purpose and output format but lacks behavioral context that would be crucial for an AI agent to use this tool effectively in production scenarios. The absence of output schema means the description should ideally explain return values more thoroughly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds minimal value beyond the schema by mentioning 'time or distance constraints' and 'single location,' which are already clear from parameter names and descriptions. The baseline score of 3 is appropriate when the schema does the heavy lifting, though the description doesn't provide additional context like parameter interactions or constraints beyond what's in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('Generate isochrone contours') and resources ('areas reachable within specified time or distance constraints from a single location'). It distinguishes itself from siblings like geocode, route-overview, and static-map by focusing on reachability analysis rather than address lookup, routing, or map generation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context through 'areas reachable within specified time or distance constraints,' suggesting it's for accessibility analysis. However, it provides no explicit guidance on when to use this tool versus alternatives like route-overview (which might provide point-to-point routing) or when not to use it. No prerequisites or sibling tool comparisons are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get high-level routing information between two or more locations. Includes travel time, distance, and an encoded polyline of the route. The result is JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| locations | Yes | ||
| costing | Yes | The method of travel to use when routing (auto = automobile). | |
| units | Yes | The unit to report distances in. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the output format ('JSON') but lacks critical details: whether this is a read-only operation, if it requires authentication, rate limits, error conditions, or what happens with invalid locations. For a routing tool with no annotation coverage, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured in two sentences: the first states purpose and key outputs, the second specifies the result format. It's front-loaded with essential information and has no wasted words, though it could be slightly more comprehensive given the lack of annotations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a routing tool with 3 required parameters, no annotations, and no output schema, the description is minimally adequate. It covers basic purpose and output format but lacks behavioral context, parameter guidance, and error handling. The absence of output schema means the description should ideally explain return values more thoroughly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 67% (2 of 3 parameters have descriptions). The description adds minimal value beyond the schema—it implies 'locations' parameter usage but doesn't explain parameter interactions or provide examples. With moderate schema coverage, the baseline of 3 is appropriate as the description doesn't significantly compensate for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Get high-level routing information'), resource ('between two or more locations'), and output details ('travel time, distance, and an encoded polyline of the route'). It distinguishes itself from siblings like geocode or isochrone by focusing on routing between multiple points rather than address conversion or area-based calculations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like isochrone (for travel-time areas) or static-map (for visual route display), nor does it specify prerequisites or exclusions. Usage context is implied but not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a PNG map image of an area, optionally including markers and a line (e.g. to draw a route or a boundary)
| Name | Required | Description | Default |
|---|---|---|---|
| style | No | The Stadia Maps style slug to use. | outdoors |
| encodedPolyline | No | The encoded polyline representing the route (precision 6). Optional, but either markers or a polyline must be specified. | |
| strokeColor | No | Optional color for the polyline (hex code or CSS color name; e.g. FFFFFF or blue). | |
| strokeWidth | No | Optional width for the route line in pixels. | |
| markers | No | Markers to add to the map. Optional, but either markers or a polyline must be specified. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool generates a PNG image but doesn't mention output format details, size limitations, rate limits, authentication needs, or error conditions. The description is minimal and lacks crucial behavioral context for a tool that produces visual output.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose ('Generate a PNG map image') and includes essential optional features. Every word earns its place with zero waste or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 5 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the PNG output contains, how large images can be, coordinate system details, or error handling. The description leaves too many behavioral aspects undefined given the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds marginal value by mentioning 'markers and a line' which corresponds to the 'markers' and 'encodedPolyline' parameters, but doesn't provide additional semantic context beyond what's in the schema. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Generate a PNG map image of an area' with specific optional features ('including markers and a line'). It distinguishes from siblings like 'geocode' (address conversion) and 'route-overview' (likely textual routing) by focusing on visual map generation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage through examples ('e.g. to draw a route or a boundary'), but doesn't explicitly state when to use this versus alternatives like 'route-overview' or 'isochrone'. It mentions that either markers or a polyline must be specified, which provides some contextual guidance but lacks explicit sibling differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the current time and zone info at any point (geographic coordinates). Output includes includes the standard UTC offset, special offset currently in effect (typically but not always Daylight Saving Time), IANA TZID, and the current timestamp in RFC 28222 format.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | The latitude of the point. | |
| lon | Yes | The longitude of the point. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the output format (UTC offset, special offset, IANA TZID, RFC 28222 timestamp) but doesn't mention error handling, rate limits, authentication needs, or whether this is a read-only operation. It adds some context but lacks comprehensive behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that efficiently conveys the tool's purpose and output details without unnecessary words. It's front-loaded with the core function and provides essential information concisely, with every element earning its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is reasonably complete. It explains what the tool does and what it returns, but could benefit from more behavioral context like error cases or usage constraints. Without an output schema, the description adequately covers the return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with clear descriptions for both lat and lon parameters. The description doesn't add any parameter-specific semantics beyond what the schema already provides, such as explaining coordinate systems or precision. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Get the current time and zone info') and the resource ('at any point (geographic coordinates)'), distinguishing it from sibling tools like geocode or route-overview which handle different geographic functions. It precisely defines what the tool does without being vague or tautological.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like bulk-geocode or isochrone, nor does it mention any prerequisites or exclusions. While the purpose is clear, there's no explicit context for usage relative to sibling tools, leaving the agent to infer based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
bulk-geocodegeocodeisochroneroute-overviewstatic-maptime-and-zone-infoEach tool has a clearly distinct purpose with no overlap: geocode and bulk-geocode handle address/POI lookups (with bulk for batch operations), isochrone generates reachability contours, route-overview provides routing information, static-map creates map images, and time-and-zone-info gives temporal data. The descriptions clearly differentiate their functions, eliminating any ambiguity.
The naming is mostly consistent with a clear snake_case pattern (e.g., bulk-geocode, static-map) and descriptive verb-noun combinations, but 'geocode' deviates slightly as a single word while others use hyphens. This minor inconsistency does not hinder readability or predictability.
With 6 tools, the count is well-scoped for a location API server, covering core functionalities like geocoding, routing, mapping, and time data. Each tool earns its place without redundancy, and the set feels complete for typical location-based tasks.
The tool surface is complete for the location API domain, offering full coverage: geocoding (single and bulk), routing, isochrone analysis, map visualization, and time/zone information. There are no obvious gaps, and agents can handle common workflows like finding places, calculating routes, and displaying maps without dead ends.
The Google Maps MCP server is a fully-managed server provided by the Maps Grounding Lite API that connects AI applications to Google Maps Platform services. It provides three main tools for building LLM applications: searching for places, looking up weather information, and computing routes with details like distance and travel time. The server acts as a proxy that translates Google Maps data into a format that AI applications can understand, enabling agents to accurately answer real-world location and travel queries.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/stadiamaps/stadiamaps-mcp-server-ts'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
