# MapIron Maps (remote · api.mapiron.com)

Geocoding, static maps and privacy-safe area maps from OpenStreetMap data. Hard caps, no overage.

- Trust score: 76/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.mapiron.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/com-mapiron-maps/v1-mcp.md), [page](https://verifymcp.io/servers/com-mapiron-maps/v1-mcp)

## Channel facts

- Endpoint: `https://api.mapiron.com/v1/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3248 tokens (~270/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the MapIron Maps MCP server?

MapIron Maps is a hosted endpoint at https://api.mapiron.com/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-mapiron-maps 'https://api.mapiron.com/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-mapiron-maps": {
      "url": "https://api.mapiron.com/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-mapiron-maps": {
      "type": "http",
      "url": "https://api.mapiron.com/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-mapiron-maps]
url = "https://api.mapiron.com/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-mapiron-maps": {
      "type": "remote",
      "url": "https://api.mapiron.com/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-mapiron-maps --url 'https://api.mapiron.com/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-mapiron-maps:
    url: "https://api.mapiron.com/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-mapiron-maps": {
      "Transport": "http",
      "Url": "https://api.mapiron.com/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-mapiron-maps -t streamable-http -u 'https://api.mapiron.com/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-mapiron-maps": {
      "type": "http",
      "url": "https://api.mapiron.com/v1/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 76, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “district_lookup” rewrote its description, which is the text the model reads
- [security] Tool “parcel_lookup” rewrote its description, which is the text the model reads
- [cosmetic] “static_map” reworded the description of “parcels”

### 2026-11-17 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 74, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 2807 → 3248
- [functional] New tool “location_profile”

### 2026-11-15 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 73, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “district_lookup” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1757 → 2807
- [functional] New tool “directions”
- [functional] New tool “distance_matrix”
- [functional] New tool “isochrone”
- [functional] New tool “place_search”
- [cosmetic] Tool “district_lookup” changed its title: Find Texas special taxing districts (MUD, WCID, PID) at a point → Find Texas and Colorado special taxing districts (MUD, WCID, PID, metro district) at a point

### 2026-11-11 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 71, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-09 (score 71)

First indexed and scored.

## MCP tools (12)

### `geocode` (~194 tokens)

Geocode an address or place

Look up an address, place name or point of interest and get coordinates (lat, lon), a readable label and address parts, from OpenStreetMap data. Use it before static_map or privacy_area_map when you only have an address. Counts 1 address lookup against the account's monthly cap. Results may be stored: up to 30 days on the Free plan, indefinitely on paid plans. Show "© OpenStreetMap contributors" with results.

Input parameters:

- `bbox` (array): [min_lon, min_lat, max_lon, max_lat]
- `lang` (string): Preferred language for names, e.g. en, de, fr
- `limit` (integer): Maximum number of matches
- `near` (object): Prefer matches near this point
- `query` (string, required): Address, place or point of interest, e.g. "233 S Wacker Dr, Chicago" or "Oswego, Illinois"

### `reverse_geocode` (~128 tokens)

Find the address at a point

Find the nearest address or place to a latitude/longitude, from OpenStreetMap data. Counts 1 address lookup against the account's monthly cap. Same storage terms and attribution as geocode.

Input parameters:

- `lang` (string): Preferred language for names, e.g. en, de, fr
- `lat` (number, required): Latitude of the point to look up, in decimal degrees (WGS84)
- `limit` (integer): Maximum number of nearby addresses or places to return
- `lon` (number, required): Longitude of the point to look up, in decimal degrees (WGS84)

### `static_map` (~341 tokens)

Render a static map image

Render a map as an image (returned inline) with optional pins (markers) and a line (path, e.g. a route). Give center and zoom, or just markers and/or path and the view is fitted automatically. Also returns a reusable image URL for web pages (add your key). Counts 1 static image against the account's monthly cap. Do not use this to show a private address such as someone's home; use privacy_area_map instead.

Input parameters:

- `center` (object): Map centre; use with zoom
- `format` (string): Image format. jpg and webp are smaller than png
- `height` (integer): Image height in CSS pixels
- `markers` (array): Pins to draw
- `padding` (integer): Space in pixels kept around markers and paths when the view is fitted automatically
- `parcel_id` (string): Highlight one parcel (a parcel_id from parcel_lookup, e.g. us-37183-0794123456); the view fits it if no center is given
- `parcels` (boolean): Draw property parcel lines (visible from zoom 13; Business plans and up). Not available on privacy_area_map
- `path` (array): A line through these points, in order
- `scale` (integer): Pixel density: 2 renders a sharper image for high-density screens at double the pixel size
- `style` (string): Map style: light (default), dark, white or grayscale
- `width` (integer): Image width in CSS pixels
- `zoom` (number): 0 = world, 10 = city, 15 = streets, 18 = buildings

### `parcel_lookup` (~206 tokens)

Find the property parcel at a point

Get the property parcel (lot) at a latitude/longitude, or by parcel_id: its boundary, the county parcel number (APN), area in m² and acres, and the public source and date. US coverage from open government data only (see mapiron.com/docs/parcels for the counties covered); owner names and values are never included. Lines are approximate and not a survey. Business plans and up; counts 1 address lookup. Results from open-licensed sources may be stored indefinitely on paid plans.

Input parameters:

- `geometry` (string): Boundary detail: simplified (about 1 m, smaller), full, or none
- `lat` (number): Latitude of a point inside the parcel (use with lon)
- `lon` (number): Longitude of a point inside the parcel (use with lat)
- `parcel_id` (string): A parcel_id from an earlier lookup, e.g. us-37183-0794123456 (instead of lat/lon)

### `district_lookup` (~393 tokens)

Find Texas and Colorado special taxing districts (MUD, WCID, PID, metro district) at a point

List the Texas special taxing districts that contain a latitude/longitude: municipal utility districts (MUD), water control and improvement districts (WCID), fresh water supply, levee and management districts statewide (TCEQ), and public improvement districts (PID) where cities publish them (coverage in the answer). For each: name, type, status, counties, the district's self-reported tax rate per $100 of taxable value with its report year, outstanding debt (Texas Comptroller), website, and the statute for the purchaser's notice (Texas Water Code §49.452 or Property Code §5.014). Colorado: every special district the Department of Local Affairs maps (metropolitan, fire, water and sanitation, library, park and others) with its certified mill levy (total, general, bond) for the tax year, county, website and the disclosure statute (C.R.S. §38-35.7-101; §38-35.7-110 for metropolitan districts); Colorado tax figures are in tax.total_mills (mills, $1 per $1,000 of assessed value), not tax.total_rate. Geocode an address first (geocode tool) or use a point inside the parcel (parcel_lookup). result is districts_found, none_found or outside_coverage. none_found is NOT proof that no district applies; near_boundary and nearby mean the lot may straddle a boundary. Report null figures as unknown, never infer a tax rate, and never say whether a notice is required: cite the statute and the district's own notice form. Business plans and up; counts 1 address lookup.

Input parameters:

- `geometry` (string): Include each district's boundary
- `include_inactive` (boolean): Also list inactive or dissolved districts
- `lat` (number, required): Latitude of the property (a point inside the parcel is best)
- `lon` (number, required): Longitude of the property

### `place_search` (~274 tokens)

Find US businesses and places by name, kind or location

Search US businesses and points of interest (restaurants, shops, banks, clinics, parks and more) from Overture Maps Places data: by name or kind of place (query), near a point (lat and lon, with radius_m), or both. Each result has name, category, address, phone and website where known, coordinates, a confidence score from 0 to 1, a stable GERS id (gers_id) that can be stored and looked up again, and its data sources with their licences. These results are not OpenStreetMap data: show the attribution returned with them. Listings can be out of date: never present a result as verified. Counts 1 address lookup against the account's monthly cap.

Input parameters:

- `category` (string): An Overture basic category, e.g. restaurant, cafe, gas_station, bank_or_credit_union, park
- `lat` (number): Latitude to search near (use with lon)
- `limit` (integer): Maximum number of places to return
- `lon` (number): Longitude to search near (use with lat)
- `query` (string): Name or kind of place, optionally with a town, state or ZIP code, e.g. coffee austin tx
- `radius_m` (number): Only places within this many metres of lat/lon

### `location_profile` (~400 tokens)

Get demographics, housing, market and hazard data for the area around a US address

A source-cited profile of the area around a US address or point (50 states, DC and Puerto Rico): population, density, age, households, income, poverty, education, employment, commute, housing units, vacancy, owner/renter share, home value, rents, rent burden, year built, building types (Census ACS 2020-2024 5-year estimates, at block group by default), population growth (Census estimates), home price change over 1 and 5 years (FHFA House Price Index by ZIP, county or metro), the latest monthly county unemployment rate (BLS) and natural hazard risk ratings for 18 hazards (FEMA National Risk Index). Each field has its value, unit, margin of error and reliability for survey estimates, the geography it describes (block_group, tract, zcta, county, cbsa, state, us), its source and vintage, and the same figure for the larger areas around it in compare. All data is U.S. government public domain. The figures describe the surrounding area, not the property: never present them as an appraisal, a flood determination or a judgement of a neighborhood, and say so when a reliability is low. Counts 10 address lookups against the monthly cap (the geocode for address is included).

Input parameters:

- `address` (string): A US street address, e.g. "1455 Riverside Dr, Austin TX" (or use lat and lon)
- `fields` (array): Field keys or sections (people, income, education_work, housing, growth, market, risk); default: everything. Field keys: GET https://api.mapiron.com/v1/location/fields
- `lat` (number): Latitude (use with lon instead of address)
- `lon` (number): Longitude (use with lat)
- `scale` (string): The smallest area to describe; fields without data at that scale come from the next larger area

### `directions` (~196 tokens)

Get a driving, truck, cycling or walking route in the US

Route between 2 to 25 points in the United States, in the order given, by car, truck, bike or foot (OpenStreetMap roads, Valhalla engine). Returns distance in metres, duration in seconds and the route line as an encoded polyline (precision 6); steps=true adds turn-by-turn instructions. Travel times are free-flow estimates with no live traffic: never present them as a live ETA. Geocode addresses first (geocode tool). Counts 1 address lookup against the monthly cap.

Input parameters:

- `alternatives` (integer): Extra alternative routes (2 points only)
- `avoid` (array): Kinds of road to avoid where possible
- `points` (array, required): Stops in travel order, each [lat, lon]
- `profile` (string): How to travel: car, truck (keeps to roads trucks may use), bike or foot
- `steps` (boolean): Include turn-by-turn instructions

### `isochrone` (~191 tokens)

Map the area reachable within a travel time or distance

Polygons of the area reachable from a US point within given travel times (minutes, up to 60) or distances (km, up to 100), by car, truck, bike or foot: service areas, delivery zones, commute sheds, catchments. Up to 4 contours; returned as GeoJSON. Free-flow travel times, no live traffic. Counts 2 address lookups per contour.

Input parameters:

- `avoid` (array): Kinds of road to avoid where possible
- `km` (array): Travel-distance contours instead of times
- `lat` (number, required): Latitude of the starting point
- `lon` (number, required): Longitude of the starting point
- `minutes` (array): Travel-time contours, e.g. [10, 20, 30]
- `profile` (string): How to travel: car, truck (keeps to roads trucks may use), bike or foot

### `distance_matrix` (~173 tokens)

Travel times and distances between many US points

Travel time (seconds) and road distance (metres) from each source to each target in the United States: up to 50 sources and 50 targets, 2,500 pairs at most. Omit targets for every source to every other. Use it to pick the nearest store or driver, or to feed a route optimiser. null means no route. Free-flow times, no live traffic. Counts 1 address lookup per pair.

Input parameters:

- `avoid` (array): Kinds of road to avoid where possible
- `profile` (string): How to travel: car, truck (keeps to roads trucks may use), bike or foot
- `sources` (array, required): Origins, each [lat, lon]
- `targets` (array): Destinations, each [lat, lon] (default: the sources)

### `privacy_area_map` (~338 tokens)

Map an approximate area without revealing the exact point

Show roughly where a place is without revealing the exact point. The point is snapped to a grid and drawn as a shaded circle that always contains the true point, with no pin; every address in the same grid cell gets the identical image, so the exact location cannot be recovered or averaged out across listings. Use it for real-estate, rental and marketplace listings, people's homes, or any location that should stay private. The image is returned inline, with a reusable URL that contains only the snapped point. Counts 1 static image against the account's monthly cap.

Input parameters:

- `color` (string): Circle colour as hex, e.g. 0f766e
- `format` (string): Image format. jpg and webp are smaller than png
- `height` (integer): Image height in CSS pixels
- `lat` (number, required): Latitude of the exact place to hide. It is snapped to the grid before use and never returned
- `lon` (number, required): Longitude of the exact place to hide. It is snapped to the grid before use and never returned
- `radius_m` (number): Minimum circle radius in metres; it is raised if needed so the circle always contains the true point
- `scale` (integer): Pixel density: 2 renders a sharper image for high-density screens at double the pixel size
- `snap_deg` (number): Grid size in degrees (0.01 is about 1 km). 0 turns snapping off and is not recommended
- `style` (string): Map style: light (default), dark, white or grayscale
- `width` (integer): Image width in CSS pixels

### `map_setup` (~137 tokens)

Get code to show an interactive map

Get ready-to-paste HTML/JavaScript for an interactive, zoomable MapIron map in a web page (MapLibre GL JS vector map, Leaflet or OpenLayers raster map), or the raster tile URL template for any other library. Replace YOUR_KEY with a key restricted to the website. Needs no key and uses no quota; the map itself counts map tiles when viewed.

Input parameters:

- `library` (string, required): maplibre = vector map (sharpest); leaflet or openlayers = raster tiles; tile_url = just the XYZ URL template
- `style` (string): Map style: light (default), dark, white or grayscale

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-mapiron-maps/v1-mcp#diagnostics

## Score history

- 2026-11-21: 76
- 2026-11-20: 76
- 2026-11-19: 75
- 2026-11-18: 75
- 2026-11-17: 75
- 2026-11-16: 74
- 2026-11-15: 74
- 2026-11-14: 73
- 2026-11-13: 73
- 2026-11-12: 72
- 2026-11-11: 72
- 2026-11-10: 71
- 2026-11-09: 71

## Common questions

### What is the MapIron Maps MCP server?

MapIron Maps is an MCP server listed in the public MCP registry as com.mapiron/maps. Geocoding, static maps and privacy-safe area maps from OpenStreetMap data. Hard caps, no overage. This page covers its hosted endpoint (https://api.mapiron.com/v1/mcp).

### Is the MapIron Maps MCP server safe to use?

MapIron Maps scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the MapIron Maps MCP server expose?

MapIron Maps exposes 12 tools: geocode, reverse_geocode, static_map, parcel_lookup, district_lookup, and 7 more. Their descriptions and schemas cost roughly 2,971 tokens of context every time the server is loaded.

### Does the MapIron Maps MCP server require authentication?

No. We connected to MapIron Maps without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the MapIron Maps MCP server still maintained?

MapIron Maps is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the MapIron Maps MCP server?

VerifyMCP ran 13 checks on MapIron Maps, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.mapiron.com/v1/mcp
- Authorisation metadata: https://api.mapiron.com/.well-known/oauth-protected-resource/v1/mcp
- Repository: https://github.com/Software-Consulting/mapiron-mcp
- Website: https://mapiron.com/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-mapiron-maps/v1-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-mapiron-maps/v1-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-mapiron-maps/v1-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-mapiron-maps/v1-mcp
