Skip to main content

Intelligent ArcGIS content search for Portal and Online.

Project description

ArcGIS MCP Server

PyPI Version PyPI - License

An AI agent tool for searching ArcGIS content (layers, maps, etc.) with natural language in VS Code using GitHub Copilot.


🚀 Quickstart Guide

This guide provides the essential steps to get the server running reliably.

Step 1: Installation

First, create a clean Python environment and install the package.

  1. Create & Activate Conda Environment:

    conda create -n arcgis-tool-env python=3.11 -y
    conda activate arcgis-tool-env
    
  2. Install from PyPI:

    pip install arcgis-mcp-server==1.1.5
    

Step 2: VS Code Configuration (Required)

A one-time manual configuration is required to guarantee VS Code can find and run the tool. This example is for developers who want to bypass the login prompt for faster testing by including credentials directly.

  1. Create a Config File: In your project folder, create a file at this exact path: .vscode/mcp.json.

  2. Paste the following JSON into the mcp.json file:

    {
      "servers": {
        "arcgis-mcp-server": {
          "type": "stdio",
          "command": "C:\\Users\\YOUR_USERNAME\\miniconda3\\envs\\arcgis-tool-env\\python.exe",
          "args": ["-m", "arcgis_mcp"],
          "env": {
            "ARCGIS_URL": "[https://your-portal.maps.arcgis.com](https://your-portal.maps.arcgis.com)",
            "ARCGIS_USERNAME": "your_username",
            "ARCGIS_PASSWORD": "your_password"
          }
        }
      }
    }
    
  3. Update the Paths and Credentials:

    • IMPORTANT: You must replace C:\\Users\\YOUR_USERNAME\\... with the actual path to the python.exe in your arcgis-tool-env. Find it by running where python in your activated terminal.
    • Replace the placeholder credentials in the "env" block with your actual ArcGIS URL, username, and password.
  4. Set Interpreter & Reload VS Code:

    • In VS Code, open the Command Palette (Ctrl+Shift+P).
    • Run Python: Select Interpreter and choose the arcgis-tool-env environment.
    • Run Developer: Reload Window from the Command Palette to apply all changes.
Want the login prompt instead?

For the standard user experience, simply remove the entire "env": { ... } block from your mcp.json file. This will cause the secure authentication pop-up to appear when you first use the tool.


Step 3: Usage

Now you can interact with the tool.

  1. Open Copilot Chat in the VS Code sidebar.
  2. Ask a Question: Tell Copilot to use your tool to find data.
    Using your ArcGIS tool, find feature layers about roads
    
  3. The tool will connect automatically using the credentials you provided and show the results.

mcp-name: io.github.esrisaudiarabia/arcgis-mcp-server

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

arcgis_mcp_server-1.1.5.tar.gz (5.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

arcgis_mcp_server-1.1.5-py3-none-any.whl (5.5 kB view details)

Uploaded Python 3

File details

Details for the file arcgis_mcp_server-1.1.5.tar.gz.

File metadata

  • Download URL: arcgis_mcp_server-1.1.5.tar.gz
  • Upload date:
  • Size: 5.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.11

File hashes

Hashes for arcgis_mcp_server-1.1.5.tar.gz
Algorithm Hash digest
SHA256 507052f06fda504a7dee73da3bc004bcc8d35ccb0d23a839c8cb08f48bbf12f5
MD5 e600a890eda2244cd57eab3416f7ebc5
BLAKE2b-256 1ca97e747eec3b35a0411cb9b9298aa15cd8f3f45e1be9c14a53da0a7c529d27

See more details on using hashes here.

File details

Details for the file arcgis_mcp_server-1.1.5-py3-none-any.whl.

File metadata

File hashes

Hashes for arcgis_mcp_server-1.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 1d5157b0be6e668276ba287884881ec3090ed9de53a8c33b4b7b412661ca5d71
MD5 3649a9fc2bc7801e8922316eedf6398b
BLAKE2b-256 b7a06889ea8a5a86620e5aa38d886e98a188531cd666d2d2af7ef5c9890bf31e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page