ArcGIS-Pro-MCP-Server
Enables AI agents to directly operate ArcGIS Pro, exposing 2,500+ geoprocessing tools for spatial analysis, data management, imagery analysis, network analysis, and mapping through natural language.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ArcGIS-Pro-MCP-ServerBuffer analysis 500m around the university"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ArcGIS-Pro-MCP-Server -- AI + GIS Smart Spatial Analysis
Let LLMs (GPT-4o, Claude, DeepSeek) directly operate ArcGIS Pro -- drive 2500+ spatial analysis tools with natural language.
What is this?
ArcGIS-Pro-MCP-Server exposes all ArcGIS Pro toolboxes as MCP (Model Context Protocol) tools, enabling:
You: "Buffer analysis 500m around the university"
AI: Auto-calls arcpy -> ArcGIS Pro -> generates resultNo tool names to memorize. No Python to write. No menus to click.
Related MCP server: arcgis-portal-mcp
Features
2500+ tools across 46 toolboxes: management(431), sa(355+), ia(328, Image Analyst), ddd(144), stats(44), ga(39), analysis(38), un/nd/tn (utility network), geoai (deep learning) + 36 more
MCP standard: works with AutoClaw, Claude Code, Codex, any MCP client
Zero dependencies: uses ArcGIS Pro's built-in Python 3.9
Security whitelist: configurable path and tool restrictions
One-click install: 30 seconds from clone to running
Also available as an Agent Skill
Prefer a ready-made agent skill (no MCP client configuration needed)? The same 2500+ tools are packaged as ArcGIS Agent — a portable skill with an agent-facing playbook, installable in one command:
GitHub repo: https://github.com/zhaojj662/arcgis-agent
Skill registry page: https://clawhub.ai/zhaojj662/skills/arcgis-agent
Install:
clawhub install arcgis-agent
Works with WorkBuddy, OpenClaw, Claude Code and any agent that reads SKILL.md.
Supported Modules
Module | Tools | Highlights |
management | 392 | Data management, projection, fields, topology |
sa (Spatial Analyst) | 355 | Slope, aspect, reclassify, viewshed, hydrology |
ia (Image Analyst) | 328 | Raster functions, image classification, deep learning |
ddd (3D Analyst) | 144 | DEM, contours, viewshed2, skyline, point cloud |
nax (Network Analyst) | 61 | Route, service area, OD matrix |
conversion | 57 | JSON/KML/CAD/Excel/raster conversion |
na | 55 | Legacy network analysis |
stats (Spatial Statistics) | 44 | Moran's I, Gi*, KDE, Ripley's K, GWR |
cartography | 44 | Contour labels, aggregation, simplification |
ga (Geostatistical) | 39 | Kriging, IDW, EBK, cross-validation |
analysis | 38 | Buffer, Clip, Intersect, Erase, Union, Thiessen |
edit | 18 | Align, extend, trim, split, merge |
server | 18 | Publish services, cache, tiles |
stpm (SpaceTime) | 16 | Space-time cube, emerging hotspots |
geocoding | 13 | Address matching, reverse geocoding |
sharing | 6 | Web layers, web maps, scene sharing |
Full runtime list: GET /modules (46 toolboxes / 2517 tools verified on ArcGIS Pro 3.x).
Quick Start
Prerequisites
Windows 10/11
ArcGIS Pro 3.x (with valid license)
Python 3.9+
Install
git clone https://github.com/zhaojj662/ArcGIS-Pro-MCP-Server.git
cd ArcGIS-Pro-MCP-Server
install.batStart Server
Double-click start_server.bat or run:
start_server.batServer runs on http://127.0.0.1:8765.
Verify:
Invoke-RestMethod http://127.0.0.1:8765/health
# {"status":"ok","server":"ArcGIS-Pro-MCP-Server","version":"2.1","tools":2517,"modules":46}Configure AI Client
AutoClaw MCP Settings:
Field | Value |
Name | arcpy |
Mode | Local process (stdio) |
Command | python |
Args | path/to/mcp_bridge.py |
Claude Code (claude_desktop_config.json):
{
"mcpServers": {
"arcpy": {
"command": "python",
"args": ["C:/Users/%USERNAME%/ArcGIS-Pro-MCP-Server/bridge/mcp_bridge.py"]
}
}
}Try It
"Buffer roads.shp by 500 meters"
"Calculate slope and aspect from this DEM"
"Hotspot analysis on crime points"
"Kriging interpolation on PM2.5 monitoring data"
"Batch viewshed for 100 observer points"Architecture
AI Client <-- stdio --> bridge/mcp_bridge.py <-- HTTP --> src/server.py (arcpy) --> ArcGIS Pro 3.xSecurity
Edit src/server.py to restrict access:
ALLOWED_PATHS = ["C:/GIS-AI-Course/"] # Only allow these directories
INCLUDE_MODULES = ["analysis", "sa"] # Only expose these modulesPaths can also be set without editing the file, via the ARCPY_ALLOWED_PATHS environment variable (semicolon-separated):
set ARCPY_ALLOWED_PATHS=C:/GIS-AI-Course/;D:/data/API
Endpoint | Method | Description |
/health | GET | Server status, tool count |
/tools | GET | List available tools (first 200) |
/modules | GET | List all modules with tool counts |
/module/{name} | GET | List every tool in one module |
/tool/{id} | GET | Look up a single tool |
/call | POST | Execute a tool |
FAQ
Q: Is ArcGIS Pro required? A: Yes. arcpy runs only inside the ArcGIS Pro Python environment.
Q: Supported ArcGIS Pro versions? A: 3.x series (tested on 3.0).
Q: Can I limit which tools AI can access?
A: Yes. Edit INCLUDE_MODULES in src/server.py.
Q: What is the relationship with arcpy-mcp-server? A: This is the renamed, current home of that project. The old URL still redirects here.
License
MIT -- see LICENSE
This server cannot be deployed
Maintenance
Related MCP Connectors
GIS tools for AI agents: 65 free tools + 8 paid (hazard/site-scouting/GeoJSON export)
- geoOAuthco.thinair
Geocoding, routing, isochrones, traffic, weather, and place search for AI agents. 19 MCP tools.
Governed app access for AI agents: 1,000+ apps & 12,000+ tools via Code Mode MCP.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables natural language control of live ArcGIS Pro sessions through the Model Context Protocol, allowing inspection of projects, layers, and attributes, and execution of geoprocessing tasks.252MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to search, query, and manage ArcGIS Portal and Online content, feature layers, users, and groups via the Model Context Protocol.21MIT
- AlicenseAqualityAmaintenanceEnables AI assistants to control ArcGIS Pro through natural language, executing geoprocessing tools, editing data, and automating GIS workflows via a persistent ArcPy session.12Apache 2.0
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to query and visualize ArcGIS Online/Enterprise geospatial data through natural language, performing spatial analysis and map generation.-