← Directory
mcp · Global
postgis-mcp
Postgis MCP Server
Claim this listing
Represent postgis-mcp? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.
What's in it
- Data offered docs-verified
- PostGIS database connection via MCP
- Formats llm-inferred
- MCP stdio
- Access docs-verified
- Open source under the ISC licence; requires your own PostgreSQL database with the PostGIS extension and connection credentials (DB_URL_n, or legacy DB_HOST/DB_NAME/DB_USER/DB_PASSWORD).
Useful for
- Use cases llm-inferred
- Let an AI assistant query consultancy PostGIS tables (site boundaries, drainage assets, constraint layers) through natural-language prompts · Map consultancy-specific table names via domain-aliases.json so natural-language table selection picks the right layer · Connect several project databases at once (DB_URL_1, DB_URL_2, DB_URL_3) to compare datasets across sites
- Audience llm-inferred
- GIS analysts · drainage engineers · hydrologists · civils engineers
Limitations
- Constraints llm-inferred
- Provides a connection only; no datasets are bundled, so data must already exist in your PostGIS database · Requires Node.js v14 or higher and a PostgreSQL instance with PostGIS · Credentials are supplied via .env or MCP env variables; the legacy single-database DB_PASSWORD form is only a fallback · Tool names and the set of spatial operations exposed are not documented, and the metadata lists no tools · No UK-specific data or coverage is described · The docs do not state whether queries are read-only · No version, release or maintenance information is given beyond the listed dependency versions
- Licence
- Unknown — check provider terms
- Authentication
- Credentials via env: DB_PASSWORD (README-verified)
- GitHub stars
- 20
- Last commit
- 21/04/2026
- Last successful page check
- 14/10/2026
- Page health
- healthy
- Package
- Not recorded
- Verification
- Not independently verified
Provenance & evidence
Tools/install/auth auto-extracted from README; quality score heuristic (stars, recency, tool count, licence).
Metadata observed 15/10/2026 · research sweep: github-search