RefConvMCP
Fetches Street View imagery for a location: checks panorama coverage near a grid reference (returning capture date plus distance and bearing to the point), then retrieves static images by panorama ID with a computed camera heading that looks toward the requested point, with support for all-round views or custom heading/pitch/fov, returned inline and optionally saved as JPEGs.
Click on "Deploy 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., "@RefConvMCP convert SU 123 456 to lat/long and show me Street View there"
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.
RefConvMCP
An MCP server that takes Ordnance Survey (British National Grid) grid references, such as SU 123 456, converts them to lat/long, and fetches Google Street View images for that spot.
"Show me Street View at NN 166 712, looking all four ways"
Tools
Tool | What it does | Cost |
| Grid ref → WGS84 lat/long, easting/northing and a Google Maps link | free, offline |
| Lat/long → grid ref (2–10 figures) | free, offline |
| Checks for a panorama near a grid ref and returns its capture date and distance/bearing to the point | free (metadata endpoint) |
| Returns Street View image(s) inline and can also save them as JPEGs | billed per image by Google |
Grid reference formats
Lettered, 0–10 digits:
SU,SU1245,SU 123 456,su123456,NN 16650 71250Numeric easting/northing in metres:
412300,145600
A grid reference is a square: 6 figures is 100 m and 8 figures is 10 m. The server uses the centre of the square and then finds the nearest outdoor Street View panorama within radius_m (default 100 m). By default it returns one image, taken from that panorama and looking towards the grid ref point. Use views=4 to get all-round coverage, or set heading, pitch and fov yourself.
The conversion uses pyproj (EPSG:27700 → EPSG:4326).
Related MCP server: mcp-postcodes
How it works
"SU 123 456"
│ 1. parse grid ref (gridref.py)
▼
easting 412350, northing 145650 (centre of the 100 m square)
│ 2. reproject OSGB36 → WGS84 (pyproj, EPSG:27700 → EPSG:4326)
▼
51.2099, -1.8246
│ 3. find nearest panorama (Street View metadata API, free)
▼
pano_id, panorama lat/long, capture date
│ 4. work out the camera heading from the panorama to the point
│ 5. fetch image(s) by pano_id (Street View Static API, billed)
▼
JPEG(s) returned to the model as MCP image content and saved to diskParsing a grid reference (
src/refconv_mcp/gridref.py). The two letters name a 100 km square on the British National Grid. The letterIisn't used, and the first letter picks a 500 km block. The server turns the letters into the square's south-west corner in metres. The digits split into an easting half and a northing half. Their scale depends on how many there are: 6 figures means each digit pair counts in 100 m steps. The server then adds half a square to get the centre. You can also enter an easting/northing in metres directly.Converting to lat/long. Easting and northing are on the OSGB36 datum with a Transverse Mercator projection. GPS and Google use WGS84. pyproj does the datum shift and projection, which is accurate to a few metres. That's well inside a 6-figure square.
latlon_to_gridrefdoes the same steps in reverse.Finding a panorama (
src/refconv_mcp/streetview.py). The Street View metadata endpoint is free. It returns the nearest outdoor panorama withinradius_m, orZERO_RESULTSif there isn't one. That way the server never pays for an image that doesn't exist.Aiming the camera. Panoramas are usually on a road, not on the grid point itself. The server calculates the compass bearing from the panorama to the point, so the default view looks at the place you asked about. With
views=N, the N headings are spread evenly around 360°, starting from that bearing.Fetching images. Each view is requested by
pano_id, so every image comes from the same panorama. The images go back to the model as MCP image content. They're also saved as<gridref>_<timestamp>_h<heading>.jpginREFCONV_OUTPUT_DIR.
The server (src/refconv_mcp/server.py) uses the official MCP Python SDK (FastMCP) and talks to the client over stdio.
Setup
1. Google API key
In Google Cloud Console, create or choose a project and enable billing. Street View has a monthly free tier.
Enable the Street View Static API under APIs & Services → Library.
Create an API key under APIs & Services → Credentials. Restrict it to the Street View Static API.
2. Install
Requires uv.
git clone https://github.com/scottejames/RefConvMCP.git
cd RefConvMCP
uv sync
cp .env.example .env && chmod 600 .env # then put your key in .env3. Register with Claude Code
claude mcp add --scope user refconv -- "$PWD/run.sh"Keeping the API key out of git
The key lives only in
.env. That file is gitignored, so it is never committed..env.exampleis the committed template.run.shsources.envand then starts the server. Claude Code is registered againstrun.sh, so the key is not stored in~/.claude.jsoneither.If an API error message contains the key, the server redacts it before returning the message to the model.
Other MCP clients can skip
run.shand setGOOGLE_MAPS_API_KEYin the environment directly.
Variable | Required | Purpose |
| yes (Street View tools only) | Google key with the Street View Static API enabled |
| no | Where images are saved ( |
Development
uv run pytestLicence
MIT. Street View imagery is © Google and subject to the Google Maps Platform Terms.
Available Tools
4 toolsgridref_to_latlonA
Convert an OS grid reference to WGS84 latitude/longitude.
Args: grid_ref: e.g. "SU 123 456", "NN166712", "TQ3080" or numeric "412300,145600". centre: return the centre of the referenced square (True) or its SW corner (False).
Inputs: grid_ref (required), centre.
latlon_to_gridrefA
Convert WGS84 latitude/longitude to an OS grid reference.
Args: lat: latitude in decimal degrees. lon: longitude in decimal degrees. digits: total figures in the reference (2-10, even). 6 = 100 m precision.
Inputs: lat (required), lon (required), digits.
streetview_coverageA
Check whether Google Street View has a panorama near a grid reference.
Uses the free metadata endpoint, so it costs nothing. Returns the panorama location, capture date, and distance/bearing to the grid reference point.
Args: grid_ref: OS grid reference, e.g. "SU 123 456". radius_m: how far from the point to search for a panorama (metres).
Inputs: grid_ref (required), radius_m.
streetview_from_gridrefA
Fetch Google Street View image(s) for an OS grid reference.
Finds the nearest outdoor panorama within radius_m of the centre of the grid square, then returns the image(s). By default one image is taken looking from the panorama towards the grid reference point.
Args: grid_ref: OS grid reference, e.g. "SU 123 456" or "NN166712". views: number of images spread evenly around 360 deg (1-8). 4 gives N/E/S/W-style coverage. heading: compass heading of the first view in degrees. Default: towards the point (or 0 if the panorama is on top of it). pitch: up/down camera angle, -90 to 90. fov: horizontal field of view in degrees, 10-120. radius_m: search radius for the nearest panorama in metres. size: image size "WxH", max 640x640. save: also save JPEGs to REFCONV_OUTPUT_DIR and return their paths.
Inputs: grid_ref (required), fov, save, size, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The conversion pair (gridref_to_latlon vs latlon_to_gridref) is unambiguous, distinguished by direction and argument names. The two Street View tools are mostly distinct (free metadata probe vs image retrieval), but streetview_coverage overlaps with the panorama-lookup step already embedded in streetview_from_gridref, so an agent may wonder which to call first.
All names use snake_case and the two conversion tools follow a clean symmetric 'a_to_b' pattern, with streetview_ prefix grouping the imagery tools. Minor deviation: 'coverage' is a noun while the others are action/prepositional phrases, but the set is still easily readable.
Four tools is tight and appropriate for a narrow conversion-plus-imagery utility, with each tool mapping to a distinct step. It is slightly on the lean side, and streetview_coverage is partially redundant with the lookup inside streetview_from_gridref.
Both conversion directions plus a coverage check and image retrieval cover the core workflow end to end. Gaps are minor: no batch conversion, no alternative datums/other national grids, and no reverse lookup of a panorama back to coordinates.
Maintenance
Related MCP Connectors
UK postcode lookup, nearest postcodes, autocomplete and distance (OS open data)
Location tools for Claude and other MCP clients, strongest in the US and Great Britain. Geocode whole lists with a confidence score per row, filter by distance, get road distances and drive-time areas, and plan multi-driver routes with Google Maps links. Check flood zones, crime and live warnings, find nearby places and UK registers (NHS, CQC, food hygiene), and keep shareable maps. Reads and writes Google Sheets. Free: sign in with Google.
Weather now and 9-day forecasts anywhere (MET Norway) and Great Britain place-name lookup
Address to coordinates and back, postal codes, worldwide (OpenStreetMap). Free, no key.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEncode latitude/longitude to geohash strings and decode geohashes to coordinates with offline, keyless operation.74 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables UK postcode lookups including geographic details, nearest postcodes, validation, and random postcode generation via the free postcodes.io API.86 npmMIT
- AlicenseAqualityBmaintenanceProvides 22 geospatial tools for coordinate conversion, geocoding, routing, terrain analysis, weather, and radio link planning, all without requiring API keys.22MIT
- AlicenseNot gradedqualityCmaintenanceProvides tools to search for KartaView street-level imagery near a location and retrieve all frames of a given sequence.72 npmMIT