mcp · Global

3dcitydb-mcp-server

A Model Context Protocol (MCP) server that gives AI assistants (Claude Code, Claude Desktop, and any MCP-compatible client) direct, natural language access to semantic 3D city models in CityGML managed within a 3DCityDB V5. Also includes an agentic Chatbot application using the MCP server with commercial or locally running LLMs.

Visit source ↗GitHub repository ↗

Feature or claim this listing

Feature this listing — founding Featured slots are 50% off for 6 months

Represent 3dcitydb-mcp-server? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: semantic 3D city models (CityGML) stored in 3DCityDB v5 · schema and attribute discovery for CityGML object classes · read-only SQL query execution against city-model data · CityGML/CityJSON/IFC import (fullstack Docker mode only)
Formats docs-verified: CityGML 1.0-3.0 · CityJSON · IFC (converted to CityGML 3.0 on import)
Access docs-verified: Open source under Apache-2.0; self-hosted against your own 3DCityDB v5 PostgreSQL instance. LLM API keys are needed only for the LangChain agent CLI and chat assistant, not for Claude Code/Desktop.

Useful for

Use cases llm-inferred: Pull building footprints and heights from a 3DCityDB for flood-risk exposure screening · Compute building volumes and 3D surface areas for drainage or civils massing studies · Import CityGML or IFC models into a 3DCityDB for consultancy review and QA · Run ad-hoc SQL summaries of city-model attributes for planning reports
Audience llm-inferred: GIS analysts · BIM/civils engineers · planners · 3D city model data managers

Limitations

Constraints docs-verified: Requires a running 3DCityDB v5 PostgreSQL instance with PostGIS · Volume and 3D area queries need PostGIS built with SFCGAL; without it they fail or return errors · Query execution is SELECT-only; writes are blocked · CityGML/CityJSON/IFC import via the chat UI is available only in fullstack Docker mode · Chat assistant needs an LLM provider (Anthropic, OpenAI, or Ollama)

Licence: Apache-2.0
Authentication: API key via env: ANTHROPIC_API_KEY, CITYDB_PASSWORD, OPENAI_API_KEY, POSTGRES_PASSWORD (auto-extracted from README)
GitHub stars: 18
Last commit: 15/10/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: pypi:3dcitydb-mcp-server
Verification: Not independently verified

Auto-extracted, unverified fields: tools, install, auth. Check upstream documentation.

Provenance & evidence

Daily discovery 2026-10-15: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 16/10/2026 · daily-2026-10-15 (github-search)