Maps, places and travel · MCP server
ArcGIS Pro MCP: MCP server, setup and security
ArcGIS Pro MCP is an open-source MCP server published on GitHub that lets an AI agent control an open ArcGIS Pro project and its geoprocessing tools. Its repository has 36 stars and its last commit is from September 6, 2026 and it is licensed under AGPL-3.0.
| Adoption (stars) | 16/40 | |
|---|---|---|
| Maintenance | 25/30 | |
| Framework (licence, registry, official) | 15/30 |
What ArcGIS Pro MCP does
According to its repository: “ArcGIS Pro add-in that lets an assistant drive the open project: layers, attributes, selections, symbology, layouts, rasters, geoprocessing tools and arcpy.”
The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. ArcGIS Pro MCP is listed under Maps, places and travel, a category of 67 servers in the directory, where it ranks #23 by stars.
Topics declared by the repository: add-in, ai-assistant, arcgis, arcgis-pro, arcpy, claude.
Installing and connecting ArcGIS Pro MCP
No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.
It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: C#. Listed systems: Windows.
Security: what to check
Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.
None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to ArcGIS Pro MCP. That does not replace reading the code.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on July 7, 2026, the Knight60/ArcGIS-Pro-MCP repository has 36 stars and 6 forks, with 0 open issues. It has more stars than 47% of the servers in the directory. Last change 2 months ago.
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
ArcGIS Pro MCP is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
Limitations
- Install from source
Alternatives
- GeoLens281 ★
- LetsFG — Flights & Hotels2.2K ★
- Google Maps MCP Server479 ★
- Cesium MCP145 ★
- Submitmap MCP261 ★
- Gondola Award Travel Search9 ★
Learn more
Frequently asked questions
How do I install ArcGIS Pro MCP?
No package is declared in the MCP registry: clone the Knight60/ArcGIS-Pro-MCP repository, follow its README, then declare the start command in your client's MCP configuration.
Is ArcGIS Pro MCP free?
The code is published under the AGPL-3.0 licence and can be used free of charge.
Is ArcGIS Pro MCP safe?
No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.
Is it an official server?
Nothing says so: it is a project published by Knight60 on GitHub. Check who maintains it before giving it access.
What are the alternatives to ArcGIS Pro MCP?
In the same category: GeoLens, LetsFG — Flights & Hotels, Google Maps MCP Server, and Cesium MCP. GeoLens and LetsFG — Flights & Hotels score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score