arcgis-mcp-bridge
Related Servers
Alternatives to arcgis-mcp-bridge
- AlicenseCqualityDmaintenanceA local MCP server that enables AI clients to read ArcGIS Pro project information and execute ArcPy geoprocessing in the native ArcGIS Pro Python environment.1387MIT
- AlicenseNot gradedqualityCmaintenanceConnects QGIS to an LLM through the Model Context Protocol, allowing agentic interaction with and control of QGIS for prompt-assisted project creation, layer loading, code execution, and more.GPL 3.0
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables MCP-capable assistants to control an open ArcGIS Pro project locally over TCP 127.0.0.1, with 68 commands and 167 tools for layers, editing, symbology, layouts, geoprocessing, and arcpy execution.1MIT
- AlicenseAqualityCmaintenanceDrive Esri's ArcGIS Pro from an AI agent — the ArcGIS Pro counterpart to QGIS MCP. A headless ArcPy CLI plus an in-process .NET 8 add-in that exposes the live Pro session as MCP tools (ping, zoom_to, query, run_gp, export_layout) so an agent drives the running project while you watch.664PolyForm Noncommercial 1.0.0
- FlicenseBqualityCmaintenanceEnables safe local MCP-based control of ArcMap Desktop 10.8, allowing read-only inspection of map documents, layers, datasets, and execution of allowlisted geoprocessing tools through ArcPy.152-
- AlicenseAqualityAmaintenanceToken-efficient Python stdio MCP server exposing safe text-file search, reading, and refactoring tools.1644 PyPI1Apache 2.0
- AlicenseBqualityDmaintenanceProduction-ready TypeScript MCP server exposing utility, GitHub, and Microsoft Teams tools over stdio.141MIT
- AlicenseCqualityBmaintenanceIt enables MCP clients to execute ArcPy-based GIS workflows within configured permission and path boundaries, manage projects, maps, layers, layouts, data, spatial analysis, networks, and publishing. It can also attach to a live ArcGIS Pro session when explicitly requested, while failing closed for unauthorized or unintended operations.458MIT
TDQS
Scored across 103 tools
Most tools have distinct names and descriptions, but at 103 tools there are several close pairs that could be confused, such as set_map_extent_from_layer vs zoom_to_layer, near_analysis vs generate_near_table, and zonal_statistics vs zonal_statistics_as_table. Descriptions generally clarify intent, but the sheer number of overlapping analysis/data-management operations makes misselection a real risk.
The overwhelming majority of tool names are snake_case and follow a descriptive verb_noun or noun_to_format pattern, which is easy to scan and predict. However, a meaningful subset uses bare noun phrases like hotspot_analysis, service_area, od_cost_matrix, hillshade, and spatial_autocorrelation, so the verb_noun convention is not perfectly uniform.
With 103 tools, the surface is far beyond the 25+ threshold and clearly in the extreme range. Even though ArcGIS is a broad platform, this many tools creates excessive selection overhead and makes the server difficult for an agent to navigate coherently.
The tool set covers an impressive breadth of vector, raster, network, QA/QC, and map/layout workflows. Notable gaps remain, however: there is no direct way to query and return feature attribute rows, and general row-level insert/update/delete operations are missing beyond append, calculate_field, and delete_identical. These gaps are workable in many workflows but represent real missing lifecycle coverage.