Search Wikidata-based filming and narrative locations, nearby places, rankings, countries, and live atlas statistics over MCP.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent โ or use 1-click editor setup below.
๐ก Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Filming Locations.
where_was_it_filmedGive a title, get the places it was shot at, each with its evidence
what_was_filmed_hereThe inverse, and the question this atlas is unusual for answering: give a place, get everything recorded as made there
search_productionsFind productions by name, accent- and case-insensitive, best match first
search_locationsFind places by name, filterable by country or kind of place
locations_nearPlaces within a radius of a WGS84 coordinate, each with `distance_km
top_locationsThe atlas ranked, worldwide or inside one country or one kind of place
The filming-locations MCP server exposes the Movie Scene Map atlas through Model Context Protocol. The atlas covers real places where films and television series were shot, along with places where video games, anime, and manga are set. Records can include coordinates, a fame ranking, related productions, and the source supporting each claim.
The data distinguishes between two relationships. Films and series use Wikidata's filming-location relation, while games, anime, and manga use its narrative-location relation. This distinction matters when an agent turns results into prose: a fictional setting should not be described as a place where something was filmed.
The factual dataset is CC0. The server itself is MIT-licensed. Photographs and linked Wikipedia text retain their own licenses.
A client sends MCP requests to the hosted Streamable HTTP endpoint at https://moviescenemap.com/mcp. The service is stateless and accepts POST requests; a GET request returning HTTP 405 is expected. The older https://thefilmmap.com/mcp address remains available for clients configured before the rename.
The atlas is built from Wikidata. Some records also include evidence extracted from an English Wikipedia Filming section or a setting category. These evidence types remain separate and identify the relevant article and section. Results may include country-level records without coordinates, because coverage is not uniform.
The hosted service requires no local installation, account, or API key. A client can use this configuration:
For self-hosting, provide the atlas file and start the Node process with ATLAS_JSON=/path/to/atlas-compact.json PORT=8896 node server.mjs. Docker can build and serve the bundled public atlas on port 8896. HOST defaults to 127.0.0.1; the container changes it to 0.0.0.0 so the service is reachable from outside the container.
The filming-locations MCP server provides these operations:
where_was_it_filmed: returns places associated with a production and their evidence.what_was_filmed_here: finds productions recorded at a supplied place.search_productions: searches production names without case or accent sensitivity, ordered by best match.search_locations: searches place names with optional country and place-kind filters.locations_near: finds places within a radius of WGS84 coordinates and reports distance_km.top_locations: ranks locations globally or within one country or place kind.list_countries: lists countries and their location counts.get_statistics: returns live aggregates by medium and place kind, plus leading countries and busiest places.A place record does not identify an individual scene. The data supports the claim that a production filmed at a place, not which scene was filmed there. Games, anime, and manga were not filmed at their narrative locations, so applications must preserve that relationship.
Coverage can be incomplete. Some productions are represented only at country level, and works without a usable placement are listed at moviescenemap.com/gaps/. Counts change with releases; current aggregate figures are available from get_statistics and the Movie Scene Map site. Data downloads are offered as GeoJSON and CSV, with the dataset also mirrored on GitHub.
Factual signals from GitHub, npm, and our automated checks โ not a rating.
No reviews yet โ be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/filming-locations)<a href="https://allmcps.com/mcp/filming-locations"><img src="https://allmcps.com/api/badge/filming-locations?style=directory" alt="Filming Locations on AllMCPs" /></a>