ArcGIS Pro Bridge MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ARCGIS_PRO_PYTHON | No | Path to the ArcGIS Pro Python executable, if automatic detection fails. | |
| ARCGIS_PRO_INSTALL_DIR | No | Path to the ArcGIS Pro installation directory, if automatic detection fails. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| detect_arcgis_environmentA | 检测 ArcGIS Pro 安装与 Python 解释器路径。 |
| pingA | 返回一个最小可验证结果，用于确认客户端已真正调用 MCP Tool。 |
| health_checkC | 返回轻量级健康检查，帮助快速判断 MCP 与 ArcGIS 环境是否可用。 |
| doctorC | 返回面向 GISer 的完整环境诊断报告。 |
| debug_runtime_contextA | 返回当前 MCP 进程的运行上下文，用于排查 Trae 或沙箱环境差异。 |
| execute_arcpy_codeC | 在 ArcGIS Pro Python 环境中执行 ArcPy 代码并返回 stdout、stderr 与异常信息。 |
| buffer_featuresC | 执行常用 Buffer 分析，返回输出要素摘要和执行信息。 |
| clip_featuresC | 执行常用 Clip 分析，返回输出要素摘要和执行信息。 |
| build_gis_resource_uriC | 根据资源类型与本地路径生成可读取的 ArcGIS Resource URI。 |
| list_gis_layersC | 列出工程中的地图、图层、字段与空间参考，并返回对应 Resource URI。 |
| inspect_project_contextC | 读取工程概览，包括布局、地图框、默认地图候选与数据源状态。 |
| inspect_gdbB | 检查 GDB 的要素类、字段与空间参考，并返回对应 Resource URI。 |
| generate_sync_planC | 数据同步逻辑的占位接口，后续可扩展为差异分析与脚本生成能力。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| server_status | 返回当前服务与 ArcGIS 环境发现状态。 |
| gis_resource_catalog | 列出当前服务提供的固定资源与模板资源。 |
| current_project_layers_resource | 读取当前 ArcGIS Pro 工程中的地图、图层、字段与空间参考。 |
| current_project_context_resource | 读取当前 ArcGIS Pro 工程的布局、地图框、默认地图候选与数据源状态。 |
TDQS
Scored across 13 tools
Several tools have overlapping diagnostic purposes (health_check, doctor, debug_runtime_context, ping, detect_arcgis_environment). While descriptions differentiate them, an agent may still struggle to pick the right one. Other tools like inspect_gdb, list_gis_layers, and build_gis_resource_uri are more distinct.
Most tools follow a verb_noun pattern (buffer_features, clip_features, build_gis_resource_uri, etc.), but 'doctor', 'health_check', and 'ping' break the pattern as nouns or noun-verb combos. The mix is noticeable but not chaotic.
13 tools is within the ideal 3-15 range for a specialized bridge server. The count feels reasonable, covering diagnostics, inspection, basic geoprocessing, and code execution without being overwhelming.
The tool surface covers core areas: environment detection, project inspection, simple spatial operations, and arbitrary arcpy execution. However, it lacks common GIS operations like intersect or dissolve, and the 'generate_sync_plan' is a placeholder. The arcpy execution tool mitigates some gaps but not all workflows are directly supported.