Macrostrat MCP Server
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| find-columnsB | Find geological stratigraphic columns, rock layers, and geological history for any location worldwide. Use for geology, bedrock, formations, age dating, and stratigraphic analysis. |
| find-unitsB | Find geological rock units, formations, bedrock geology, and mineral information for any location worldwide. Use for geology questions, rock types, age dating, lithology, and geological analysis. |
| defsC | Routes giving access to standard fields and dictionaries used in Macrostrat |
| defs-autocompleteB | Quickly retrieve all definitions matching a query. Limited to 100 results |
| mineral-infoC | Get information about a mineral, use one property |
| timescaleC | Get information about a time period |
| lat-lng-to-tileA | Convert latitude/longitude coordinates to map tile coordinates (x, y) for a given zoom level. Uses the same web mercator projection as MapKit. |
| map-tilesA | Get map tile URLs from the Macrostrat tiles server. Use lat-lng-to-tile tool first to get proper x,y coordinates. Defaults to 'carto' scale which automatically adapts detail level to zoom. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| geologic-history | Get the geologic history of a location |
| bedrock | Get information about bedrock geology |
| geologic-map | Generate map tiles for visualizing geology of an area |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| api_response | JSON schema for the standard Macrostrat API response wrapper containing success metadata and data array |
| units | JSON schema for the response from the units endpoint |
| columns | JSON schema for the response from the columns endpoint |
| minerals | JSON schema for the response from the defs/minerals endpoint |
| lithologies | JSON schema for the response from the defs/lithologies endpoint |
| environments | JSON schema for the response from the defs/environments endpoint |
| timescales | JSON schema for the response from the defs/timescales endpoint |
| intervals | JSON schema for the response from the defs/intervals endpoint |
| econs | JSON schema for the response from the defs/econs endpoint |
| strat_names | JSON schema for the response from the defs/strat_names endpoint |
| structures | JSON schema for the response from the defs/structures endpoint |
| measurements | JSON schema for the response from the defs/measurements endpoint |
TDQS
Scored across 8 tools
Most tools have distinct purposes, but 'find-columns' and 'find-units' overlap significantly in their descriptions (both for geological analysis of locations), which could cause confusion. Other tools like 'defs' and 'defs-autocomplete' are clearly related but serve different functions, while tools like 'lat-lng-to-tile' and 'map-tiles' are distinct but interdependent.
The naming is inconsistent with mixed conventions: some use snake_case ('lat-lng-to-tile'), some use kebab-case ('defs-autocomplete'), and others use plain words ('defs', 'timescale'). There is no predictable verb_noun pattern, making it harder for agents to infer tool purposes from names alone.
With 8 tools, the count is reasonable for a geological data server, covering definitions, location-based queries, mapping, and mineral/time information. It's slightly under the ideal 10-15 range for comprehensive coverage but not overly sparse, fitting the domain scope adequately.
The tool set covers core geological data access (definitions, units, columns, minerals, timescales) and mapping functions, but there are notable gaps such as missing update/delete operations for data manipulation and limited query capabilities (e.g., no advanced filtering or aggregation tools). It supports basic retrieval but lacks full lifecycle coverage.