A secure, local-first MCP server exposing ArcGIS Pro's ArcPy engine over stdio JSON-RPC.
A secure, local-first MCP server exposing ArcGIS Pro's ArcPy engine over stdio JSON-RPC.
arcgis-mcp-bridge requires Windows, a licensed ArcGIS Pro installation, and Python 3.11 or newer for the bridge package.
arcgis-mcp-bridge - An existing writable directory for ARCGIS_MCP_ALLOWED_ROOTS - An existing file geodatabase for ARCGIS_MCP_SCRATCH_GDB, unless <first allowed root>\scratch.gdb already existsCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"arcgis-mcp-bridge": {
"command": "C:\\...\\envs\\arcgis-mcp-env\\python.exe",
"args": [
"-m",
"arcgis_mcp.server"
],
"env": {
"ARCPY_PYTHON_PATH": "C:\\...\\envs\\arcgis-mcp-env\\python.exe",
"ARCGIS_MCP_ALLOWED_ROOTS": "C:\\GIS\\Data;C:\\Workspace",
"ARCGIS_MCP_SCRATCH_GDB": "C:\\GIS\\Data\\scratch.gdb",
"ARCGIS_MCP_MAX_WORKERS": "2"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
arcgis-mcp-bridge - An existing writable directory for ARCGIS_MCP_ALLOWED_ROOTS - An existing file geodatabase for ARCGIS_MCP_SCRATCH_GDB, unless <first allowed root>\scratch.gdb already exists| Variable | Description | Required |
|---|---|---|
| ARCPY_PYTHON_PATH | Declared in the maintainer’s client configuration. | Yes |
| ARCGIS_MCP_ALLOWED_ROOTS | Declared in the maintainer’s client configuration. | Check documentation |
| ARCGIS_MCP_SCRATCH_GDB | Declared in the maintainer’s client configuration. | Check documentation |
| ARCGIS_MCP_MAX_WORKERS | Declared in the maintainer’s client configuration. | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
AI-powered changelog ai MCP server for agents. Supports parse changelog, generate entry, bum...
This server provides **6 essential tools**, **2 resources**, and **1 prompt template** for text classification:
The TypeScript framework for MCP
Publish HTML, Markdown, KV, JSON, and files to brewpage.app from AI assistants. No signup.