What it does
The server exposes Mappls, India's maps platform, to MCP-compatible AI agents. Its tools cover search and geocoding (converting addresses to coordinates and back, autocomplete, keyword and nearby search, place details, address standardisation and 6-digit pincode validation), routing and navigation (turn-by-turn directions, traffic-aware ETAs, distance matrices, points of interest along a route and snapping GPS points to roads), and utilities (elevation, straight-line distance and static map image URLs).
An agent would reach for it when it needs location data for Indian addresses and places, for example finding the nearest hospital or ATM, getting an address from coordinates, checking whether a pincode is valid or getting driving directions between two areas. The publisher notes that it was built because no MCP server existed for India-first location data.
Running it requires a Mappls API key, obtained from a free account by creating a Cloud project and copying its Static Key. The key is set as an environment variable and the server is added to an MCP client such as Claude Desktop, Cursor or Windsurf. Coordinates are given in decimal degrees, and poi_along_route needs the encoded polyline from a get_directions response. The project is released under the MIT licence.
Limitations and requirements
Requires a Mappls account and a Static Key set as an environment variable. The IP whitelist field is left blank for unrestricted access. Usage is subject to Mappls free-tier API limits.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.AmanMakesStuff/mappls-mcp
MCP server for Mappls (MapMyIndia) — India-first maps API for AI agents
v2.0.0As shown on registry.modelcontextprotocol.io when we last read it