sentaurus-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SENTAURUS_MCP_CONFIG | Yes | Absolute path to the Sentaurus MCP configuration JSON file. | |
| SENTAURUS_ENABLE_ACTIONS | No | Set to '1' to allow creating and submitting experiments; leave at '0' for read-only operation. | 0 |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_experimentsA | List persistent experiments, paginated. Read-only. |
| get_experimentC | Read execution state, process IDs, timing, manifest and validation label. |
| create_experimentC | Prepare input files; each stage specifies tool and input_file. Tool commands come from operator config. Does not run. Native batch folder, not an SWB project. |
| submit_experimentA | Launch a prepared experiment asynchronously. Duplicate requests do not restart it. Poll status; no fixed runtime kill. |
| read_logB | Read bounded log increments; cursor offset is bytes. |
| list_artifactsB | Index native files; does not read large TDR files into model context. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| capabilities |
TDQS
Scored across 6 tools
Each tool targets a distinct resource/action: listing vs fetching experiment metadata, preparing vs launching an experiment, reading logs vs listing files. No two tools have overlapping purposes.
All tools follow a consistent verb_noun snake_case pattern (list_experiments, get_experiment, create_experiment, submit_experiment, read_log, list_artifacts). There is no mixing of conventions or vague verbs.
Six tools is well-scoped for an experiment management server, covering the essential lifecycle without bloat. Each tool serves a clear, necessary role.
The surface covers the main workflow: create, submit, monitor (get/read_log), and list artifacts. Missing operations like delete/cancel or update are not explicitly present, but the core experiment lifecycle is well served and the absence is a minor gap.