The data-intelligence layer of the Forge suite
Ask for geospatial data by intent and get back the best-fit correct dataset — ranked by coverage and resolution, with access cost as the deciding tiebreaker — across fourteen heterogeneous source types. ForgeGIS computes, ForgeMind reasons, ForgeGIS Studio renders; ForgeData decides which data to use and how to get it.
Three short answers for the technical evaluator.
ForgeData sits beneath the suite and owns the cross-cutting problem of data discovery and access. It keeps one catalog — what you can query and the recipes that refresh it — and routes every request to the best-fit dataset across local files and remote services alike, with no hardcoded paths and no per-project glue.
Most platforms make the customer build the routing layer themselves: bespoke catalog tables, hand-maintained config, hardcoded paths nobody wants to own. ForgeData ships that layer in the box, so the suite works against a realistic, scattered data landscape on day one rather than after an integration project.
The catalog is the configuration — the data-source recipes live in the same GeoPackage file as the inventory, so nothing drifts out of sync, and API keys stay in the environment, never the file. Routing is fidelity-first: coverage, then resolution, then extent-fit, with access cost as the deciding tiebreaker.
ForgeData's core differentiator. Name an operation and an area of interest, and find_optimal_for_operation returns a ranked, costed, deduplicated list of catalog entries that can serve it — with no hardcoded paths.
After the first read of a remote dataset, ForgeData stores the measured wall-clock latency and uses it instead of the static formula — the cost signal sharpens the longer the suite runs.
Fourteen source-type implementations cover the common public and private geospatial sources — all addressable through one uniform query interface. The customer's environment can be a mix; the caller sees one ranked answer.
The same correctness discipline the rest of the Forge suite is built on, applied to data.
All state — datasets and the recipes that refresh them — lives in one standard
GeoPackage. No companion sources.yml to drift out of sync, and no secrets baked
in: the catalog stores only the environment-variable name that holds a key. Safe to copy, ship
to a field laptop or air-gapped site, or commit — and readable in QGIS or DB Browser.
Tool failures return a structured envelope with a specific, machine-readable reason
— aoi_out_of_coverage, windowed_read_unsupported,
bbox_invalid — and an empty answer always says why, never the nearest wrong tile. For
coverage gaps it even names the registered source whose sync could acquire the area.
SRTM flattens open water to a literal 0 m that reads as solid ground. Given a water-mask layer, ForgeData recodes over-water cells to NoData at its elevation read seam, so point, region, profile and polygon elevation answers over a coastline are honest — whichever source they come from: SRTM, Copernicus, 3DEP, Terrarium or remote WCS. A strict no-op until a water layer is present.
When the suite is installed for everyone on a workstation, each user keeps a private catalog and also reads a shared, read-only one for the whole machine. Publishing a folder to the shared catalog takes Administrator approval, so what everyone sees is curated. Seaglass Globe scenarios can be registered in the catalog by reference, beside the data they sit on.
When ForgeGIS computes a slope raster over an area, the result registers back into the catalog as a derived product that records the operation and parameters that made it. The next request that needs the same thing finds it instead of recomputing it — so over a long-running project, more of what the suite needs is already in the catalog.
The routing work could in principle live inside ForgeGIS, ForgeMind, or Studio. It deliberately does not — each of those has a sharp job, and folding data-intelligence concerns into any of them would blur that boundary. ForgeData is the home for the cross-cutting problem, so it can evolve independently of every consumer.
ForgeMind (and Seaglass Globe) run ForgeData as an MCP server over stdio — the same JSON-RPC surface any third-party MCP client could use — while ForgeGIS Studio embeds it in-process as a Java library, and all of them read the same catalogs. ForgeGIS is consumed by ForgeData as an in-process Java library for the actual data reads, so windowed-raster extraction and elevation queries happen with no network hop. Underlying sources stay exactly where they are.
One layer, three readers. Each one-pager leads with the parts of ForgeData that matter most to that audience.
Its catalog is a single local file with no embedded secrets, so a curated catalog and the data it references ship together to a field laptop or air-gapped site and query on arrival. Fail-closed on coverage, content hashes on published files, honest elevation over water.
Download defense & IC one-pager (PDF)An MCP server an agent hands a data question to — which dataset covers this area at the right resolution, and what does it cost to read? — and gets back a ranked, costed answer instead of a hardcoded path, with structured errors an agent can branch on.
Download agent-builder one-pager (PDF)When a ForgeMind workflow asks for a viewshed or a slope analysis, the agent does not need to know one dataset is a local SRTM tile and another a remote COG on S3. It calls one operation and gets back a ranked, costed list — best-fit correct dataset first.
Download general sales one-pager (PDF)All ForgeData collateral. Direct download — no email gate, no form wall.
The catalog model and the shared machine catalog, cost-aware routing, the operation registry, all fourteen source types, the MCP tool surface and its 1.2.5 reply bounds, the read paths, and deployment guidance. Updated for 1.2.5.
Download PDFFront/back overview. General-purpose first-touch document covering positioning, the routing story, and who ForgeData is for.
Download PDFFor defense and intelligence programs and prime integrators. Leads on the secret-free portable catalog, fail-closed coverage, and disconnected deployment.
Download PDFFor AI agent builders and MCP-native runners. Leads on the MCP surface, intent-based routing, structured refusal, and derived-product memory.
Download PDFEvaluation access, suite licensing, and partnership inquiries — we read every email. An evaluation build is available to qualified teams on request.
rich@seaglassfoundry.com