> ## Documentation Index
> Fetch the complete documentation index at: https://docs.footstep.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools

> Routing, geocoding, natural-language, and prediction tools available to your agent

The MCP server exposes 15 tools. Click any tool for details.

### Routing

| Tool                                                  | What it does                                                                                                                          |
| ----------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
| [`get_directions`](/mcp/tools/get-directions)         | Get driving, walking, or cycling directions between locations. Returns distance, duration, turn-by-turn steps, and terrain analytics. |
| [`optimize_stops`](/mcp/tools/optimize-stops)         | Find the fastest order to visit multiple stops. Returns optimised route with distance/time savings.                                   |
| [`compare_routes`](/mcp/tools/compare-routes)         | Compare walk vs bike vs drive between the same locations. Side-by-side distance, duration, and terrain difficulty.                    |
| [`find_and_route`](/mcp/tools/find-and-route)         | Find a place by name and get directions to it in one step. Combines geocoding and routing.                                            |
| [`get_isochrone`](/mcp/tools/get-isochrone)           | Find everywhere reachable within a time or distance limit from a starting point. Returns a polygon boundary.                          |
| [`get_matrix`](/mcp/tools/get-matrix)                 | Calculate travel times and distances between every combination of origins and destinations.                                           |
| [`get_elevation`](/mcp/tools/get-elevation)           | Get elevation data for a list of coordinates. Returns heights and summary statistics.                                                 |
| [`snap_trace`](/mcp/tools/snap-trace)                 | Clean up a GPS trace and get road surface, class, speed, and terrain details.                                                         |
| [`search_along_route`](/mcp/tools/search-along-route) | Find places along a route ranked by how little detour they add.                                                                       |

### Geocoding

| Tool                                            | What it does                                                                            |
| ----------------------------------------------- | --------------------------------------------------------------------------------------- |
| [`geocode`](/mcp/tools/geocode)                 | Convert an address or place name to coordinates. Returns lat/lng with confidence score. |
| [`reverse_geocode`](/mcp/tools/reverse-geocode) | Convert coordinates to an address. Find what's at a given lat/lng.                      |
| [`batch_geocode`](/mcp/tools/batch-geocode)     | Geocode up to 1,000 addresses in one call.                                              |
| [`search_places`](/mcp/tools/search-places)     | Find places and points of interest near a location.                                     |

### Natural Language

| Tool                                        | What it does                                                                                                                              |
| ------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| [`parse_address`](/mcp/tools/parse-address) | Clean up messy free-text addresses. Fixes typos, expands abbreviations, and infers missing fields. Useful as a pre-step before geocoding. |

### Predict

| Tool                                          | What it does                                                                                                     |
| --------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |
| [`get_prediction`](/mcp/tools/get-prediction) | Generate spatial probability predictions for missing person scenarios. Returns per-hex scores across an H3 grid. |

## Example prompts

Once connected, you can ask your AI agent things like:

* "Get me walking directions from Kings Cross to Tower Bridge"
* "Should I walk or cycle? Compare both options"
* "Directions to the nearest train station from here"
* "Find coffee shops near my hotel"
* "Are there any petrol stations on my way to Cambridge?"
* "What's the elevation profile between these two coordinates?"
* "How far can I cycle in 15 minutes from Liverpool Street station?"
* "Find the best order to visit these 8 delivery stops"
* "Clean up this GPS trace from my bike ride and show me the terrain"
* "Geocode these 5 addresses and tell me which ones are in London"
* "Clean up this messy CSV of customer addresses before geocoding them"

The agent will call the appropriate Footstep tool and interpret the results for you.

## Rate limits

MCP tool calls use your API key and count against the same rate limits as direct API calls. See the [authentication guide](/authentication) for rate limit details.