Mapsmith
OfficialClick on "Install 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., "@Mapsmithfind parcels within 300m of rivers in parcels.gpkg and rivers.gpkg, with provenance"
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.
Mapsmith π¨πΊοΈ
Professional-grade geoprocessing for AI agents β with provenance you can verify.
Mapsmith is an open-source MCP server that gives any AI agent (Claude, ChatGPT, Copilot, Cursor, or your own) real GIS analysis capabilities: not just "make me a map", but buffers, overlays, reprojections, zonal statistics, terrain and network analysis β executed by deterministic engines, never hallucinated by the model.
Ask for the result. The agent picks the tools. Every output carries its full lineage.
Why Mapsmith
Real geoprocessing, not map CRUD. Built on the proven open geospatial stack (GDAL, GeoPandas, Shapely, and more to come: WhiteboxTools, PDAL, DuckDB Spatial, QGIS Processing via sidecar).
Provenance by design. Every layer Mapsmith produces ships with a machine-readable lineage manifest: source datasets (with checksums), every tool executed, exact parameters, CRS decisions, software versions, timestamps. Re-run it bit-identical, without the LLM. No AI slop.
The LLM orchestrates, tools compute. Geometry and numbers only ever come from deterministic tool executions β never from model output.
Semantic tools, not a tool dump. A curated set of goal-level tools plus a searchable operation catalog (progressive discovery), because agent accuracy collapses when you expose hundreds of raw tools.
Related MCP server: NodeAPI
Quickstart
# Docker (the supported path)
docker run -i --rm -v $(pwd)/data:/data ghcr.io/mapsmith-ai/mapsmith
# or from PyPI
uvx mapsmithAdd to Claude Desktop / any MCP client (stdio):
{
"mcpServers": {
"mapsmith": {
"command": "uvx",
"args": ["mapsmith"]
}
}
}Then ask your agent things like:
"Take parcels.gpkg, keep only the parcels within 300 m of the river in rivers.gpkg, and give me the result with the analysis lineage."
Tools (v0.1)
Tool | What it does |
| CRS, geometry types, schema, extent, feature count of any vector dataset |
| Metric buffer with automatic UTM estimation for geographic CRS |
| Clip a layer with a mask layer |
| Reproject to any CRS (EPSG code or WKT) |
| Join attributes by spatial predicate (intersects/within/contains) |
| Return the full lineage manifest of any Mapsmith output |
| Searchable catalog of available operations (progressive discovery) |
Every tool that writes an output also writes <output>.provenance.json next to it.
Provenance example
{
"mapsmith_version": "0.1.0",
"operation": "buffer_layer",
"parameters": {"distance_meters": 300.0},
"inputs": [{"path": "rivers.gpkg", "sha256": "9f2cβ¦", "crs": "EPSG:4326"}],
"crs_decisions": {"analysis_crs": "EPSG:32632", "reason": "estimated UTM zone for metric buffering"},
"engine": {"name": "geopandas", "version": "1.0.1"},
"started_at": "2026-08-18T10:15:03Z",
"finished_at": "2026-08-18T10:15:04Z"
}Architecture
AI agent (Claude / ChatGPT / Copilot / your app)
β MCP (stdio local Β· Streamable HTTP remote)
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββ
β Mapsmith server β
β Β· semantic tools + operation catalog β
β Β· parameter validation, CRS discipline β
β Β· provenance recorder (lineage manifests) β
βββββββββββββββββββββββββββββββββββββββββββββββ€
β Engines β
β Β· vector: GeoPandas/Shapely (built-in) β
β Β· raster: Rasterio (roadmap) β
β Β· terrain/hydro: WhiteboxTools (roadmap) β
β Β· qgis_process / GRASS sidecar (roadmap, β
β GPL-isolated via subprocess) β
βββββββββββββββββββββββββββββββββββββββββββββββRoadmap
Raster engine (Rasterio): zonal stats, clip, hillshade, algebra
WhiteboxTools adapter: terrain & hydrology (500+ permissive tools)
QGIS Processing sidecar (subprocess-isolated): ~900 algorithms
Sandboxed code-execution tool for the long tail
Remote server (Streamable HTTP + OAuth), long-job progress via MCP Tasks
Map rendering: shareable MapLibre viewer URLs, MCP Apps
Install support policy
Docker (or uvx on a machine with working wheels) is the only supported installation path. Geospatial native dependencies across three OSes are a support black hole; issues about broken local environments will be redirected here.
License
Mapsmith server and engines: AGPL-3.0-or-later (see
LICENSE)Client SDK and tool-schema definitions (future
sdk/): Apache-2.0
You can self-host Mapsmith freely, forever. If you modify it and offer it as a service, the AGPL asks you to share your changes β or talk to us about a commercial license.
"Mapsmith" is a trademark of the Mapsmith project β see TRADEMARKS.md.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceEnables advanced geospatial analysis including elevation queries, line-of-sight calculations, terrain visualization, and autonomous drone mission planning with real-time safety analysis and 3D visualization capabilities.MIT
- Flicense-qualityDmaintenanceMachine-native GIS processing API for AI agents and developers. Convert, reproject, validate, repair, buffer, clip, dissolve, and tile vector geodata across 25 endpoints. Pay-per-use USDC on Solana Mainnet ($0.01/op). No accounts, no API keys. Remote MCP SSE.
- Flicense-qualityDmaintenanceExposes ArcGIS Pro geoprocessing capabilities to LLMs via the arcpy library, enabling automated spatial analysis and data management. It provides a comprehensive suite of tools for vector geoprocessing, terrain analysis, and raster operations designed for GIS workflows.4

Magic Lane MCP Serverofficial
AlicenseBqualityBmaintenanceEnables AI agents to become geospatially intelligent assistants with tools for location search, smart routing, round trip planning, reverse geocoding, isochrone analysis, route visualization, geofence management, and interactive map display.8377Apache 2.0
Related MCP Connectors
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Precision math engine for AI agents. 203 exact methods. Zero hallucination.
Build, validate, and deploy multi-agent AI solutions from any AI environment.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mapsmith-ai/mapsmith'
If you have feedback or need assistance with the MCP directory API, please join our Discord server