drillsite-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host to bind when running over a network transport. Default for the --host CLI flag. | 127.0.0.1 |
| MCP_PORT | No | Port to bind when running over a network transport. Default for the --port CLI flag. | 8001 |
| LOG_LEVEL | No | stderr log level. | INFO |
| MCP_TRANSPORT | No | Transport used by the server. Default for the --transport CLI flag (stdio, sse, or streamable-http). | stdio |
| DRILLSITE_API_KEY | No | API key sent to the backend as the X-API-Key header. | dev-key |
| DRILLSITE_API_URL | No | Backend base URL of the Drill-site Prospectivity API. | http://127.0.0.1:8000 |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_zonesA | List candidate drill zones at or above a score, best first. |
| get_zoneA | Get one zone with its score, the drivers behind it, and field notes. |
| rank_zonesA | Rank the top N zones to drill first, with the main driver of each score. |
| add_field_noteA | Attach a short field observation to a zone. This writes to the backend. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| drill_plan | Ask the agent for a drill plan grounded in the server's tools. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| all_zones | All zones, best score first. |
TDQS
Scored across 4 tools
list_zones and rank_zones both return zones ordered by score, so an agent may hesitate between threshold-based listing and top-N ranking. The descriptions do distinguish filtering from ranking and driver emphasis, but the overlap is real. get_zone and add_field_note are clearly distinct.
All tools follow a consistent snake_case verb_noun pattern: list_zones, get_zone, rank_zones, add_field_note. Singular/plural use is also predictable for one-zone versus many-zone operations.
Four tools is well-scoped for a drill-zone ranking and field-note server. Each tool supports a distinct part of the workflow without excessive surface area.
The core workflow of finding, inspecting, ranking, and annotating zones is covered. The main gap is that field notes are append-only, with no update or delete operation, which is a minor but noticeable lifecycle limitation.