GIS MCP Server
GIS MCP 服务器
模型上下文协议 (MCP) 服务器实现,使用 GIS 库(当前支持 Shapely 和 PyProj)将大型语言模型 (LLM) 连接到 GIS 操作,使 AI 助手能够执行地理空间操作和转换。
阿尔法
0.2.0(Alpha)版本正在积极开发中。我们欢迎各位贡献代码并加入我们,共同构建这个项目。
🎥 演示
Related MCP server: GeoServer MCP Server
📋 目录
🚀 功能
🔍 全面的几何运算(交集、并集、缓冲等)
🌐 高级坐标变换和投影
📏 精确的距离和面积计算
🗺️ 空间分析和验证
🛠️ 轻松与 MCP 兼容客户端集成
📋 先决条件
Python 3.10 或更高版本
MCP 兼容客户端(如 Claude Desktop 或 Cursor)
用于软件包安装的互联网连接
🛠️ 安装
选择最适合您需要的安装方法:
📦pip安装
建议大多数用户使用 pip 安装:
安装 uv 包管理器:
pip install uv创建虚拟环境(Python 3.10+):
uv venv --python=3.10安装软件包:
uv pip install gis-mcp启动服务器:
gis-mcppip 配置
要使用 Claude 或 Cursor 的 pip 安装,请添加以下配置:
克劳德桌面:
视窗:
{
"mcpServers": {
"gis-mcp": {
"command": "C:\\Users\\YourUsername\\.venv\\Scripts\\gis-mcp",
"args": []
}
}
}Linux/Mac:
{
"mcpServers": {
"gis-mcp": {
"command": "/home/YourUsername/.venv/bin/gis-mcp",
"args": []
}
}
}Cursor IDE (创建.cursor/mcp.json ):
视窗:
{
"mcpServers": {
"gis-mcp": {
"command": "C:\\Users\\YourUsername\\.venv\\Scripts\\gis-mcp",
"args": []
}
}
}Linux/Mac:
{
"mcpServers": {
"gis-mcp": {
"command": "/home/YourUsername/.venv/bin/gis-mcp",
"args": []
}
}
}配置后:
确保将
YourUsername替换为您的实际用户名对于开发安装,请将
/path/to/gis-mcp替换为项目的实际路径重新启动 IDE 以应用更改
您现在可以通过 Claude 或 Cursor 使用所有 GIS 操作!
🛠️ 开发安装
对于贡献者和开发者:
安装 uv 包管理器:
pip install uv创建虚拟环境:
uv venv --python=3.10以开发模式安装包:
uv pip install -e .启动服务器:
python -m gis_mcp开发配置
要使用 Claude 或 Cursor 的开发安装,请添加以下配置:
克劳德桌面:
视窗:
{
"mcpServers": {
"gis-mcp": {
"command": "C:\\path\\to\\gis-mcp\\.venv\\Scripts\\python",
"args": ["-m", "gis_mcp"]
}
}
}Linux/Mac:
{
"mcpServers": {
"gis-mcp": {
"command": "/path/to/gis-mcp/.venv/bin/python",
"args": ["-m", "gis_mcp"]
}
}
}Cursor IDE (创建.cursor/mcp.json ):
视窗:
{
"mcpServers": {
"gis-mcp": {
"command": "C:\\path\\to\\gis-mcp\\.venv\\Scripts\\python",
"args": ["-m", "gis_mcp"]
}
}
}Linux/Mac:
{
"mcpServers": {
"gis-mcp": {
"command": "/path/to/gis-mcp/.venv/bin/python",
"args": ["-m", "gis_mcp"]
}
}
}配置后:
确保将
YourUsername替换为您的实际用户名对于开发安装,请将
/path/to/gis-mcp替换为项目的实际路径重新启动 IDE 以应用更改
您现在可以通过 Claude 或 Cursor 使用所有 GIS 操作!
🛠️ 可用工具
Shapely 操作
基本操作
工具 | 描述 |
| 使用可自定义的参数在几何体周围创建缓冲区 |
| 查找两个几何体的交集 |
| 组合两个几何体 |
| 寻找几何图形之间的差异 |
| 查找几何之间的对称差异 |
几何特性
工具 | 描述 |
| 计算几何体的凸包 |
| 获取几何体的边界框 |
| 获取几何体的最小旋转矩形 |
| 获取几何体的质心 |
| 获取几何体的边界 |
| 获取几何体的坐标 |
| 获取几何体的类型 |
变换
工具 | 描述 |
| 以指定的角度和原点旋转几何体 |
| 使用 x 和 y 因子缩放几何体 |
| 使用 x、y 和 z 偏移平移几何体 |
高级操作
工具 | 描述 |
| 创建几何体的三角剖分 |
| 根据点创建 Voronoi 图 |
| 创建多个几何体的联合 |
测量
工具 | 描述 |
| 获取几何的长度 |
| 获取几何体的面积 |
验证和简化
工具 | 描述 |
| 检查几何是否有效 |
| 使几何有效 |
| 简化具有指定公差的几何体 |
PyProj 操作
坐标变换
工具 | 描述 |
| 在 CRS 之间转换坐标 |
| 在 CRS 之间投影几何体 |
CRS信息
工具 | 描述 |
| 获取有关 CRS 的详细信息 |
| 获取所有可用 CRS 的列表 |
| 获取给定坐标的 UTM 区域 |
| 获取给定坐标的 UTM CRS |
| 获取给定坐标的地心 CRS |
大地测量计算
工具 | 描述 |
| 获取有关大地测量计算的信息 |
| 计算点之间的大地距离 |
| 计算给定距离和方位角的点 |
| 使用大地测量计算多边形的面积 |
🛠️ 客户端开发
工具使用示例:
缓冲区操作
Tool: buffer
Parameters: {
"geometry": "POINT(0 0)",
"distance": 10,
"resolution": 16,
"join_style": 1,
"mitre_limit": 5.0,
"single_sided": false
}坐标变换
Tool: transform_coordinates
Parameters: {
"coordinates": [0, 0],
"source_crs": "EPSG:4326",
"target_crs": "EPSG:3857"
}大地距离
Tool: calculate_geodetic_distance
Parameters: {
"point1": [0, 0],
"point2": [10, 10],
"ellps": "WGS84"
}🔮 计划功能
添加对更多 GIS 库的支持 - GDAL/OGR
实施高级空间索引
添加对光栅操作的支持
实现网络分析功能
添加对 3D 几何体的支持
实施性能优化
🤝 贡献
欢迎您贡献力量!您可以通过以下方式提供帮助:
分叉存储库
创建功能分支(
git checkout -b feature/AmazingFeature)提交您的更改(
git commit -m 'Add some AmazingFeature')推送到分支(
git push origin feature/AmazingFeature)打开拉取请求
请确保您的 PR 描述清晰地描述了问题和解决方案。如适用,请包含相关的问题编号。
📄 许可证
该项目根据 MIT 许可证获得许可 - 有关详细信息,请参阅 LICENSE 文件。
🔗 相关项目
📞 支持
如需支持,请在 GitHub 存储库中打开一个问题。
🏆 徽章
Available Tools
87 toolsadbscanB
Adaptive DBSCAN clustering (requires coordinates, no dependent_var).
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold, +2 more. Returns: object
append_gpdC
Reads two shapefiles directly, concatenates them vertically.
Inputs: shapefile1_path (required), shapefile2_path (required), output_path (required). Returns: object
bufferC
Create a buffer around a geometry.
Inputs: geometry (required), distance (required), resolution, join_style, +2 more. Returns: object
build_and_transform_weightsB
Build and transform spatial weights in one step.
Parameters:
data_path: Path to point shapefile or GeoPackage
method: 'queen', 'rook', 'distance_band', or 'knn'
id_field: Optional field name for IDs
threshold: Distance threshold (required if method='distance_band')
k: Number of neighbors (required if method='knn')
binary: True for binary weights, False for inverse distance (DistanceBand only)
transform_type: 'r', 'v', 'b', 'o', or 'd'
Inputs: data_path (required), method, id_field, threshold, +3 more. Returns: object
build_transform_and_save_weightsA
Pipeline: Read shapefile, build spatial weights, optionally transform, and save to file.
Parameters:
data_path: Path to point shapefile or GeoPackage
method: 'queen', 'rook', 'distance_band', 'knn'
id_field: Optional field name for IDs
threshold: Distance threshold (required if method='distance_band')
k: Number of neighbors (required if method='knn')
binary: True for binary weights, False for inverse distance (DistanceBand only)
transform_type: 'r', 'v', 'b', 'o', or 'd' (optional)
output_path: File path to save weights
format: 'gal' or 'gwt'
overwrite: Allow overwriting if file exists
Inputs: data_path (required), method, id_field, threshold, +6 more. Returns: object
calculate_geodetic_areaC
Calculate area of a polygon using geodetic calculations.
Inputs: geometry (required), ellps. Returns: object
calculate_geodetic_distanceC
Calculate geodetic distance between points.
Inputs: point1 (required), point2 (required), ellps. Returns: object
calculate_geodetic_pointC
Calculate point at given distance and azimuth.
Inputs: start_point (required), azimuth (required), distance (required), ellps. Returns: object
clip_raster_with_shapefileA
Clip a raster dataset using polygons from a shapefile and write the result. Converts the shapefile's CRS to match the raster's CRS if they are different.
Parameters:
raster_path_or_url: local path or HTTPS URL of the source raster.
shapefile_path: local filesystem path to a .shp file containing polygons.
destination: local path where the masked raster will be written.
Inputs: raster_path_or_url (required), shapefile_path (required), destination (required). Returns: object
clip_vectorC
Clip vector geometries using geopandas.clip. Args: gdf_path: Path to the input geospatial file. clip_path: Path to the clipping geometry file. output_path: Optional path to save the result. Returns: Dictionary with status, message, and output info.
Inputs: gdf_path (required), clip_path (required), output_path. Returns: object
compute_ndviB
Compute NDVI (Normalized Difference Vegetation Index) and save to GeoTIFF.
Parameters:
source: input raster path.
red_band_index: index of red band (1-based).
nir_band_index: index of near-infrared band (1-based).
destination: output NDVI raster path.
Inputs: source (required), red_band_index (required), nir_band_index (required), destination (required). Returns: object
concat_bandsA
Concatenate multiple single-band raster files into one multi-band raster, handling alignment issues automatically.
Parameters:
folder_path: Path to folder containing input raster files (e.g. GeoTIFFs).
destination: Path to output multi-band raster file.
Notes:
Files are read in sorted order by filename.
If rasters have mismatched CRS, resolution, or dimensions, they are aligned automatically.
Inputs: folder_path (required), destination (required). Returns: object
convex_hullC
Calculate convex hull of a geometry.
Inputs: geometry (required). Returns: object
differenceC
Find difference between geometries.
Inputs: geometry1 (required), geometry2 (required). Returns: object
dissolve_gpdB
Dissolve geometries by attribute using geopandas.dissolve. Args: gdf_path: Path to the geospatial file. by: Column to dissolve by (optional). output_path: Optional path to save the result. Returns: Dictionary with status, message, and output info.
Inputs: gdf_path (required), by, output_path. Returns: object
distance_band_weightsA
Create a distance-based spatial weights (W) object from point data.
data_path: path to point shapefile or GeoPackage
threshold: distance threshold for neighbors (in CRS units, e.g., meters)
binary: True for binary weights, False for inverse distance weights
id_field: optional attribute name to use as observation IDs
Inputs: data_path (required), threshold (required), binary, id_field. Returns: object
dynamic_lisaC
Run dynamic LISA (directional LISA) with giddy.directional.Rose.
Returns sector counts, angles, vector lengths, and (optionally) permutation p-values.
Inputs: shapefile_path (required), value_columns (required), target_crs, weights_method, +6 more. Returns: object
envelopeC
Get bounding box of a geometry.
Inputs: geometry (required). Returns: object
explode_gpdA
Split multi-part geometries into single parts using geopandas.explode. Args: gdf_path: Path to the geospatial file. output_path: Optional path to save the result. Returns: Dictionary with status, message, and output info.
Inputs: gdf_path (required), output_path. Returns: object
extract_bandA
Extract a specific band from a multi-band raster and save it as a single-band GeoTIFF.
Parameters:
source: path or URL of the input raster.
band_index: index of the band to extract (1-based).
destination: path to save the extracted band raster.
Inputs: source (required), band_index (required), destination (required). Returns: object
focal_statisticsB
Compute focal (moving window) statistics on a raster. Args: raster_path: Path to the input raster. statistic: Statistic to compute ('mean', 'min', 'max', 'std'). size: Window size (odd integer). output_path: Optional path to save the result. Returns: Dictionary with status, message, and output path if saved.
Inputs: raster_path (required), statistic (required), size, output_path. Returns: object
gamma_statisticC
Compute Gamma Statistic for spatial autocorrelation.
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold. Returns: object
gearys_cC
Compute Global Geary's C Autocorrelation Statistic.
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold. Returns: object
geojson_to_geometryB
Convert GeoJSON to a Shapely geometry using shapely.geometry.shape. Args: geojson: GeoJSON dictionary. Returns: Dictionary with status, message, and geometry as WKT.
Inputs: geojson (required). Returns: object
geometry_to_geojsonA
Convert a Shapely geometry (WKT) to GeoJSON using shapely.geometry.mapping. Args: geometry: WKT string of the geometry. Returns: Dictionary with status, message, and GeoJSON representation.
Inputs: geometry (required). Returns: object
get_areaC
Get the area of a geometry.
Inputs: geometry (required). Returns: object
get_available_crsB
Get list of available CRS.
Inputs: no named parameters. Returns: object
get_boundsC
Get the bounds of a geometry.
Inputs: geometry (required). Returns: object
get_centroidB
Get the centroid of a geometry.
Inputs: geometry (required). Returns: object
get_coordinatesC
Get the coordinates of a geometry.
Inputs: geometry (required). Returns: object
get_crs_infoC
Get information about a CRS.
Inputs: crs (required). Returns: object
get_geocentric_crsC
Get geocentric CRS for given coordinates.
Inputs: coordinates (required). Returns: object
get_geod_infoD
Get information about a geodetic calculation.
Inputs: ellps, a, b, f. Returns: object
get_geometry_typeC
Get the type of a geometry.
Inputs: geometry (required). Returns: object
getis_ord_gC
Compute Getis-Ord G for global hot spot analysis.
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold. Returns: object
getis_ord_g_localC
Local Getis-Ord G.
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold. Returns: object
get_lengthC
Get the length of a geometry.
Inputs: geometry (required). Returns: object
get_raster_crsA
Retrieve the Coordinate Reference System (CRS) of a raster dataset.
Opens the raster (local path or HTTPS URL), reads its DatasetReader.crs attribute as a PROJ.4-style dict, and also returns the WKT representation.
Inputs: path_or_url (required). Returns: object
get_utm_crsC
Get UTM CRS for given coordinates.
Inputs: coordinates (required). Returns: object
get_utm_zoneC
Get UTM zone for given coordinates.
Inputs: coordinates (required). Returns: object
gm_lagC
Run spreg.GM_Lag (spatial 2SLS / GMM-IV spatial lag model) on a cross-section.
Returns coefficients with SE/z/p, fit metrics, (optional) AK test, and a small data preview.
Inputs: shapefile_path (required), y_col (required), x_cols (required), target_crs, +11 more. Returns: object
hillshadeA
Generate hillshade from a DEM raster. Args: raster_path: Path to the DEM raster. azimuth: Sun azimuth angle in degrees. angle_altitude: Sun altitude angle in degrees. output_path: Optional path to save the hillshade raster. Returns: Dictionary with status, message, and output path if saved.
Inputs: raster_path (required), azimuth, angle_altitude, output_path. Returns: object
intersectionC
Find intersection of two geometries.
Inputs: geometry1 (required), geometry2 (required). Returns: object
is_validC
Check if a geometry is valid.
Inputs: geometry (required). Returns: object
join_countsD
Global Binary Join Counts.
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold. Returns: object
join_counts_localD
Local Join Counts.
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold. Returns: object
knn_weightsB
Create a k-nearest neighbors spatial weights (W) object from point data.
data_path: path to point shapefile or GeoPackage
k: number of nearest neighbors
id_field: optional attribute name to use as observation IDs
Inputs: data_path (required), k (required), id_field. Returns: object
make_validC
Make a geometry valid.
Inputs: geometry (required). Returns: object
merge_gpdB
Merges two shapefiles based on common attribute columns, This function performs a database-style join, not a spatial join. Args: left_shapefile_path: Path to the left shapefile. The geometry from this file is preserved. right_shapefile_path: Path to the right shapefile to merge. output_path: Path to save the merged output shapefile. how: Type of merge. One of 'left', 'right', 'outer', 'inner'. Defaults to 'inner'. on: Column name to join on. Must be found in both shapefiles. left_on: Column name to join on in the left shapefile. right_on: Column name to join on in the right shapefile. suffixes: Suffix to apply to overlapping column names.
Inputs: shapefile1_path (required), shapefile2_path (required), output_path (required). Returns: object
metadata_rasterA
Open a raster dataset in read-only mode and return metadata.
This tool supports two modes based on the provided string:
A local filesystem path (e.g., "D:\Data\my_raster.tif").
An HTTPS URL (e.g., "https://example.com/my_raster.tif").
The input must be a single string that is either a valid file path on the local machine or a valid HTTPS URL pointing to a raster.
Inputs: path_or_url (required). Returns: object
minimum_rotated_rectangleC
Get minimum rotated rectangle of a geometry.
Inputs: geometry (required). Returns: object
moran_localD
Local Moran's I.
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold. Returns: object
morans_iC
Compute Moran's I Global Autocorrelation Statistic.
Inputs: shapefile_path (required), dependent_var, target_crs, distance_threshold. Returns: object
nearest_point_on_geometryB
Find the nearest point on geometry2 to geometry1 using shapely.ops.nearest_points. Args: geometry1: WKT string of the first geometry (e.g., a point). geometry2: WKT string of the second geometry. Returns: Dictionary with status, message, and the nearest point as WKT.
Inputs: geometry1 (required), geometry2 (required). Returns: object
normalize_geometryA
Normalize the orientation/order of a geometry using shapely.normalize. Args: geometry: WKT string of the geometry. Returns: Dictionary with status, message, and normalized geometry as WKT.
Inputs: geometry (required). Returns: object
ols_with_spatial_diagnostics_safeB
Safe MCP pipeline: Read shapefile, build/load W, convert numeric, check NaNs, run OLS.
Parameters:
data_path: path to shapefile or GeoPackage
y_field: dependent variable column name
x_fields: list of independent variable column names
weights_path: optional path to existing weights file (.gal or .gwt)
weights_method: 'queen', 'rook', 'distance_band', or 'knn' (used if weights_path not provided)
id_field: optional attribute name to use as observation IDs
threshold: required if method='distance_band'
k: required if method='knn'
binary: True for binary weights (DistanceBand only)
Inputs: data_path (required), y_field (required), x_fields (required), weights_path, +5 more. Returns: object
overlay_gpdB
Overlay two GeoDataFrames using geopandas.overlay. Args: gdf1_path: Path to the first geospatial file. gdf2_path: Path to the second geospatial file. how: Overlay method ('intersection', 'union', 'identity', 'symmetric_difference', 'difference'). output_path: Optional path to save the result. Returns: Dictionary with status, message, and output info.
Inputs: gdf1_path (required), gdf2_path (required), how, output_path. Returns: object
point_in_polygonB
Check if points are inside polygons using spatial join (predicate='within'). Args: points_path: Path to the point geospatial file. polygons_path: Path to the polygon geospatial file. output_path: Optional path to save the result. Returns: Dictionary with status, message, and output info.
Inputs: points_path (required), polygons_path (required), output_path. Returns: object
project_geometryC
Project a geometry between CRS.
Inputs: geometry (required), source_crs (required), target_crs (required). Returns: object
raster_algebraA
Perform algebraic operations (addition or subtraction) on two raster bands, handling alignment issues automatically.
Parameters:
raster1: Path to the first raster (.tif).
raster2: Path to the second raster (.tif).
band_index: Index of the band to process (1-based index).
operation: Either "add" or "subtract" to specify the calculation.
destination: Path to save the result as a new raster.
The function aligns rasters if needed, applies the selected operation, and saves the result.
Inputs: raster1 (required), raster2 (required), band_index (required), operation (required), +1 more. Returns: object
raster_band_statisticsB
Calculate min, max, mean, and std for each band of a raster.
Parameters:
source: path to input raster (local or URL).
Inputs: source (required). Returns: object
raster_histogramB
Compute histogram of pixel values for each band.
Parameters:
source: path to input raster.
bins: number of histogram bins.
Inputs: source (required), bins. Returns: object
read_file_gpdB
Reads a geospatial file and returns stats and a data preview.
Inputs: file_path (required). Returns: object
reclassify_rasterA
Reclassify raster values using a mapping dictionary. Args: raster_path: Path to the input raster. reclass_map: Dictionary mapping old values to new values (e.g., {1: 10, 2: 20}). output_path: Path to save the reclassified raster. Returns: Dictionary with status and message.
Inputs: raster_path (required), reclass_map (required), output_path (required). Returns: object
reproject_rasterA
Reproject a raster dataset to a new CRS and save the result.
Parameters:
source: local path or HTTPS URL of the source raster.
target_crs: target CRS string (e.g., "EPSG:4326").
destination: local filesystem path for the reprojected raster.
resampling: resampling method: "nearest", "bilinear", "cubic", etc.
Inputs: source (required), target_crs (required), destination (required), resampling. Returns: object
resample_rasterA
Resample a raster dataset by a scale factor and save the result.
Parameters:
source: local path or HTTPS URL of the source raster.
scale_factor: multiplicative factor for width/height (e.g., 0.5 to halve resolution, 2.0 to double).
resampling: resampling method name: "nearest", "bilinear", "cubic", etc.
destination: local filesystem path for the resampled raster.
Inputs: source (required), scale_factor (required), resampling (required), destination (required). Returns: object
rotate_geometryC
Rotate a geometry.
Inputs: geometry (required), angle (required), origin, use_radians. Returns: object
save_resultsA
MCP Tool: Save any GIS-MCP result dict to files, only when the user requests.
Args: data: The dictionary returned by any GIS-MCP tool. filename: Base filename without extension. formats: List of formats to save (default = all). folder: Target folder (relative to configured storage directory, or absolute path).
Returns: Dict with 'saved_files' mapping format -> path.
Inputs: data (required), filename, formats, folder. Returns: object
scale_geometryC
Scale a geometry.
Inputs: geometry (required), xfact (required), yfact (required), origin. Returns: object
simplifyC
Simplify a geometry.
Inputs: geometry (required), tolerance (required), preserve_topology. Returns: object
sjoin_gpdB
Spatial join between two GeoDataFrames using geopandas.sjoin. Args: left_path: Path to the left geospatial file. right_path: Path to the right geospatial file. how: Type of join ('left', 'right', 'inner'). predicate: Spatial predicate ('intersects', 'within', 'contains', etc.). output_path: Optional path to save the result. Returns: Dictionary with status, message, and output info.
Inputs: left_path (required), right_path (required), how, predicate, +1 more. Returns: object
sjoin_nearest_gpdB
Nearest neighbor spatial join using geopandas.sjoin_nearest. Args: left_path: Path to the left geospatial file. right_path: Path to the right geospatial file. how: Type of join ('left', 'right'). max_distance: Optional maximum search distance. output_path: Optional path to save the result. Returns: Dictionary with status, message, and output info.
Inputs: left_path (required), right_path (required), how, max_distance, +1 more. Returns: object
snap_geometryC
Snap one geometry to another using shapely.ops.snap. Args: geometry1: WKT string of the geometry to be snapped. geometry2: WKT string of the reference geometry. tolerance: Distance tolerance for snapping. Returns: Dictionary with status, message, and snapped geometry as WKT.
Inputs: geometry1 (required), geometry2 (required), tolerance (required). Returns: object
spatial_markovB
Run giddy Spatial Markov on a panel (n regions x t periods) from a shapefile.
Inputs: shapefile_path (required), value_columns (required), target_crs, weights_method, +8 more. Returns: object
symmetric_differenceC
Find symmetric difference between geometries.
Inputs: geometry1 (required), geometry2 (required). Returns: object
tile_rasterC
Split a raster into square tiles of a given size and save them individually.
Parameters:
source: input raster path.
tile_size: size of each tile (e.g., 256 or 512).
destination_dir: directory to store the tiles.
Inputs: source (required), tile_size (required), destination_dir (required). Returns: object
transform_coordinatesC
Transform coordinates between CRS.
Inputs: coordinates (required), source_crs (required), target_crs (required). Returns: object
translate_geometryC
Translate a geometry.
Inputs: geometry (required), xoff (required), yoff (required), zoff. Returns: object
triangulate_geometryC
Create a triangulation of a geometry.
Inputs: geometry (required). Returns: object
unary_union_geometriesC
Create a union of multiple geometries.
Inputs: geometries (required). Returns: object
unionD
Combine two geometries.
Inputs: geometry1 (required), geometry2 (required). Returns: object
voronoiC
Create a Voronoi diagram from points.
Inputs: geometry (required). Returns: object
weighted_band_sumA
Compute a weighted sum of all bands in a raster using specified weights.
Parameters:
source: Path to the input multi-band raster file.
weights: List of weights (must match number of bands and sum to 1).
destination: Path to save the output single-band raster.
Inputs: source (required), weights (required), destination (required). Returns: object
weights_from_shapefileA
Create a spatial weights (W) from a shapefile using contiguity.
contiguity: 'queen' or 'rook' (default 'queen')
id_field: optional attribute name to use as observation IDs
Inputs: shapefile_path (required), contiguity, id_field. Returns: object
write_file_gpdA
Export a GeoDataFrame to a file (Shapefile, GeoJSON, GPKG, etc.). Args: gdf_path: Path to the input geospatial file. output_path: Path to save the exported file. driver: Optional OGR driver name (e.g., 'ESRI Shapefile', 'GeoJSON', 'GPKG'). Returns: Dictionary with status and message.
Inputs: gdf_path (required), output_path (required), driver. Returns: object
write_rasterA
Write a numpy array to a raster file using metadata from a reference raster. Args: array: 2D or 3D list (or numpy array) of raster values. reference_raster: Path to a raster whose metadata will be copied. output_path: Path to save the new raster. dtype: Optional data type (e.g., 'float32', 'uint8'). Returns: Dictionary with status and message.
Inputs: array (required), reference_raster (required), output_path (required), dtype. Returns: object
zonal_statisticsB
Calculate statistics of raster values within polygons (zonal statistics). Args: raster_path: Path to the raster file. vector_path: Path to the vector file (polygons). stats: List of statistics to compute (e.g., ["mean", "min", "max", "std"]). Returns: Dictionary with status, message, and statistics per polygon.
Inputs: raster_path (required), vector_path (required), stats. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 87 tools
Many tools have overlapping functionality (e.g., union vs unary_union_geometries, merge_gpd vs append_gpd, build_transform_and_save_weights vs build_and_transform_weights, getis_ord_g vs getis_ord_g_local, morans_i vs moran_local). Some tools like 'read_file_gpd' vs 'write_file_gpd' are clearly opposite, but the presence of near-duplicates creates ambiguity.
Naming is inconsistent: some tools use verb_noun (e.g., get_centroid, buffer, union), some include '_gpd' suffix (e.g., merge_gpd, sjoin_gpd), some are camelCase (e.g., morans_i, adbscan), and some are longer descriptive phrases (e.g., build_transform_and_save_weights). No clear pattern emerges across the entire set.
With 87 tools, this far exceeds the typical well-scoped count (3-15). Even for a comprehensive GIS server, this is excessive, and many tools are near-duplicates or could be combined, leading to cognitive overload and increased risk of misselection.
The surface covers an extensive range of vector, raster, and spatial statistics operations, including CRUD-like file operations, geometry analysis, raster processing, and spatial autocorrelation. Minor gaps exist (e.g., no explicit raster classification or network analysis), but the domain is well-covered overall.
Maintenance
Related MCP Connectors
Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server for Japan geodata: cadastral lot numbers (chiban) and reverse geocoding, for AI agents.
The Google Maps MCP server is a fully-managed server provided by the Maps Grounding Lite API that connects AI applications to Google Maps Platform services. It provides three main tools for building LLM applications: searching for places, looking up weather information, and computing routes with details like distance and travel time. The server acts as a proxy that translates Google Maps data into a format that AI applications can understand, enabling agents to accurately answer real-world location and travel queries.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that connects Claude AI to QGIS, enabling direct interaction with the GIS software for project creation, layer manipulation, code execution, and processing algorithms through natural language prompts.1510Creative Commons Zero v1.0 Universal
- AlicenseAqualityDmaintenanceA Model Context Protocol server that connects Large Language Models to the GeoServer REST API, enabling AI assistants to query and manipulate geospatial data through natural language.997MIT
- AlicenseAqualityDmaintenanceAn MCP server that gives LLMs access to geographic data conversion tools, enabling transformations between different formats like WKT, GeoJSON, CSV, TopoJSON, and KML, as well as performing reverse geocoding.912 npm18MIT
- FlicenseNot gradedqualityDmaintenanceA geographic ontology layer MCP server that exposes hierarchical relations, topological adjacency, toponym disambiguation, spatial operations, and geo-constraint verification, enabling LLMs to reason with geographic structures instead of raw SQL.-