well-data-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_sourcesA | List the state regulator well-data sources this server can query: coverage, agency, searchable filters, and caveats. Call this first to see what is available. |
| search_wellsA | Search state regulator well databases by operator, well/lease name, county, field, status, or type. Returns normalized records (API number, name, operator, status, type, field, county, lat/lon, dates, depths where available) plus source-specific extras. All *Date fields are normalized to ISO 'YYYY-MM-DD' strings (or null) regardless of how the source stores them, so they sort and compare across states. Filters combine with AND. Set count_only=true to size a query before pulling records. |
| get_wellA | Look up a specific well by API number and return its FULL raw record from the state source plus the normalized summary. Handles formatting differences (dashes, state prefixes): tries an exact match first, then the bare digits, then a dash-tolerant contains-match on the county + sequence digits — so undashed input still finds wells in sources that store dashed APIs (NM, ND, CO, NV). If state is omitted, tries every state. |
| wells_nearA | Find wells within a radius of a lat/lon point — e.g. all wells on or around a pad, lease, or project site. Searches the geographically relevant sources unless state/source is given. |
| raw_queryA | Escape hatch: run a raw SQL-92 WHERE clause against one source's ArcGIS layer and get raw attributes back. Use list_sources for source keys; field names are the layer's own (see the searchableFilters mapping, or query with where='1=1' limit=1 to inspect a record). Useful for filters the normalized search does not cover (dates, depths, cumulative production). |
| list_operatorsA | Find the exact operator name strings a state uses (they rarely match what you would guess — 'Fervo Energy Company', 'CALIFORNIA RESOURCES PRODUCTION CORPORATION'). Returns distinct operator names containing the search text, per source. Use before search_wells when an operator search returns nothing. |
| search_gem_projectsA | Search bundled Global Energy Monitor tracker data: geothermal power units worldwide (Geothermal Power Tracker - covers Kenya/Olkaria, New Zealand, Guadeloupe/Bouillante, Guatemala, US) and upstream oil & gas fields/discoveries (Oil & Gas Extraction Tracker - covers Namibia Orange Basin, Guatemala, NZ). Project/field level, NOT well level. Filters are ANDed, case-insensitive substrings. Local data - fast, works offline. Cite 'Global Energy Monitor' when publishing results. |
| search_geothermal_datasetsA | Search U.S. DOE-funded geothermal project datasets via OSTI Data Explorer - this indexes the Geothermal Data Repository (gdr.openei.org): well logs, stimulation and flow-test data, microseismic, DTS, geologic models. THE source for Fervo Cape Station (search 'cape egs' or 'fervo' - note 'cape station' also matches Cape Grim air station), Utah FORGE, and some international geothermal studies. Terms are ANDed. Returns titles, DOIs, dates, and links to the data. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Tools are largely distinct: search_wells, raw_query, and wells_near differ by query mode, while search_gem_projects and search_geothermal_datasets target separate datasets. The only mild ambiguity is between the three 'search_*' tools, but descriptions clearly specify data source and query style.
Most tools follow a clear list_/search_/get_ verb_noun pattern, making the set predictable. raw_query and wells_near break that pattern, but they are still readable and not confusing.
8 tools is well-scoped for the domain: source discovery, operator lookup, normalized search, spatial proximity, raw SQL escape hatch, and specialized project/dataset searches. Each tool earns its place without redundancy.
The surface covers the full read-only workflow: discover sources, inspect operators, query wells by attributes or location, retrieve full records by API, and fall back to raw SQL when needed. The specialized GEM and OSTI searches add meaningful coverage beyond state well data.