MCP Server¶

rustgis-cli mcp runs RustGIS as a Model Context Protocol server, so an AI agent such as Claude Code, Claude Desktop, Cursor, VS Code or Codex can make maps with it. The agent opens data, runs any RustGIS command or geoprocessing tool, reads attribute tables, looks at the map as an image and looks things up in this documentation.

rustgis-cli mcp --sample                 # the World Atlas sample
rustgis-cli mcp --data parcels.geojson   # your own data (--data more than once, or --project p.rgis)
rustgis-cli mcp --yes                    # also allow file and network access

The server talks over standard input and output, so you don't start it yourself: you tell your agent how to start it (below), and the agent runs it. Each agent gets its own project, held in memory until the agent saves it.

Adding it to an agent¶

Claude Code:

claude mcp add rustgis -- rustgis-cli mcp --sample

Codex:

codex mcp add rustgis -- rustgis-cli mcp --sample

Claude Desktop (claude_desktop_config.json), Cursor (~/.cursor/mcp.json) and other clients that use an mcpServers list:

{
  "mcpServers": {
    "rustgis": {
      "command": "rustgis-cli",
      "args": ["mcp", "--sample"]
    }
  }
}

VS Code (.vscode/mcp.json):

{
  "servers": {
    "rustgis": {
      "type": "stdio",
      "command": "rustgis-cli",
      "args": ["mcp", "--sample"]
    }
  }
}

If the agent can't find rustgis-cli, give its full path (see Installation). Then ask, for example:

"Which 5 countries have the largest GDP? Show them on the map."
"Buffer the cities by 200 km, colour the result by population and show me the map."
"Load ~/data/parcels.geojson, label the parcels with their owner and export the map to parcels.png." (this reads and writes files, so it needs --yes)

Tools¶

Tool	What it does
`list_layers`	The map: its layers (name, type, feature count, fields, visibility, selection), basemap, centre and scale
`view_map`	The map as a PNG image, at the current view
`search_commands`	Finds RustGIS commands by words: their ids, ribbon locations and parameters
`run_command`	Runs a command by id with JSON parameters; each run is one undo step
`search_tools`	Finds geoprocessing tools by words
`describe_tool`	A geoprocessing tool's parameters
`run_tool`	Runs a geoprocessing tool; its output is added to the map as a new layer
`read_features`	A layer's attribute rows, optionally only those matching a where clause, sorted
`search_docs`	Searches this documentation and returns the best matching sections
`read_doc`	Reads a documentation page as Markdown, or one section of it

These are the AI Assistant's tools, plus view_map and the documentation tools. Every page of this documentation is also a resource (rustgis://docs/cli.md, rustgis://docs/user-guide/maps.md…) that a client can attach to a conversation.

What the agent may do¶

Your agent asks you before each tool call, and the server adds its own limits:

Commands that read or write files, connect to an address on the internet or run a plugin's command run only when the server was started with --yes, as does opening a project from text (it could bring in web layers). Without it, the agent can still work with the data you gave the server and with the built-in sample, basemaps and geoprocessing. view_map draws the web tile layers the project you opened already has, fetching their tiles.
Plugin management, scripts, tasks, models and the GeoLibre runner are never run from here.
Opening, replacing and undoing in the project are allowed: the project is the agent's own, not the one open in the desktop app.

Installed plugins load first, as with the other subcommands (--no-plugins skips them). Notes such as "MCP server ready" go to standard error; standard output carries only the protocol.