mcp · Global

cronotopia

Offline-first spatio-temporal database and map server in Go. Query Wikidata, Wikipedia, and OSM vector tiles with embedded neural search, all from a single SQLite file.

Visit source ↗GitHub repository ↗

Claim this listing

Represent cronotopia? 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: Wikidata entities, coordinates, dates and claims (historical events) · Wikipedia article sections with full-text (FTS5) index · OpenStreetMap vector map tiles (PBF/MVT) · Embedding-based semantic and hybrid search over article text · Spatio-temporal search by radius, year, month and day
Formats docs-verified: SQLite database file (.db, or read-only seekable .zst) · PBF/MVT vector tiles · MCP over JSON-RPC 2.0 (HTTP POST, SSE GET) · REST API (HTTP GET)
Access docs-verified: Self-hosted local install; no network needed once the database is populated; no auth in entry metadata; GPL-3.0 licence (entry metadata)

Useful for

Use cases llm-inferred: Desk-study site history: historical events within a radius of a project site, offline · Background research on named historic features or landmarks via Wikipedia article sections · Offline basemap vector tiles for report or desk-study map production
Audience llm-inferred: GIS analysts · environmental consultants (desk study) · planners

Limitations

Constraints llm-inferred: Database must be populated first: download a prebuilt database or ingest large Wikidata/Wikipedia dumps, which is slow · Content is Wikidata, Wikipedia and OSM derived; the docs describe no UK-specific, engineering or environmental datasets · No live or current data: the docs describe offline querying of stored records · Compressed .zst databases are read-only; ingestion and --ai-sync need an uncompressed database · CPU embedding sync is slow for large dumps; docs recommend an external embeddings API · Build from source requires Go 1.22 or later · Entry metadata lists tools (query, mode, latitude, ...) that match REST API parameters; the docs name MCP tools search_events, search_knowledge and get_article, so verify before use

Licence: GPL-3.0
Authentication: Unknown — review source docs
GitHub stars: 2
Last commit: 15/10/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

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

Provenance & evidence

Daily discovery 2026-10-16: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 14/10/2026 · daily-2026-10-16 (github-search)