Geoda

GeoDa TM is built upon several open source libraries and source-code files.

GeoDa is the flagship program of the GeoDa Center, following a long line of software tools developed by Dr. Luc Anselin. It is designed to implement techniques for exploratory spatial data analysis (ESDA) on lattice data (points and polygons). The free program provides a user friendly and graphical interface to methods of descriptive spatial data analysis, such as spatial autocorrelation statistics, as well as basic spatial regression functionality. The latest version contains several new features such as full space-time data support in all views, a new cartogram, a refined map movie, parallel coordinate plot, 3D visualization, conditional plots (and maps) and spatial regression.

Since its initial release in February 2003, GeoDa's user numbers have increased exponentially, as the chart and map of global users above shows. This includes lab users at universities such as Harvard, MIT, and Cornell. The user community and press embraced the program enthusiastically, calling it a "hugely important analytic tool," a "very fine piece of software," an "exciting development" and more.

Please read the detail instructions under directory BuildTools/

Note: contributions of build scripts under other platforms are welcomed, please follow the structure of building script under BuildTools/.

The built-in MCP server ships a skill, the spatial data analysis workbook, and serves it to MCP clients itself: an agent that connects to GeoDa can read it with nothing installed. It exposes two MCP tools: list_command returns the catalog (each command's id, group and parameters), and execute_command {name: "", arguments: {...}} runs one. The same text reaches a client four ways:

• execute_command {name: "skill/get", arguments: {uri: "skill://spatial-analysis-workbook"}} - the skill/get command (listed by skill/list), so a client that does not expose MCP resources can still read the skill.
• The resource skill://spatial-analysis-workbook, via resources/read.
• The prompt spatial-analysis-workbook, via prompts/get. Its section argument loads one part: workflow, overview, maps, weights, global, local, rates, multivariate, clustering.
• The instructions that initialize returns, which name the skill and how to read it.

The text lives in three files, and all three have to be edited together: