ultratribe-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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| system_diagnosticsA | Returns hardware info, CUDA capability, VRAM, and UltraTribe framework status. |
| benchmark_inferenceC | Runs synthetic in-memory benchmark to test model speed (ms/batch), throughput, and VRAM footprint. |
| list_supported_studiesA | Lists available neural decoding studies (Algonauts 2025, BOLD5000, Wen 2017, Lebel 2023). |
| get_atlas_regionsC | Retrieves Human Connectome Project (HCP) cortical or Harvard-Oxford subcortical ROI regions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| System Status | Live health and hardware resource utilization |
| Studies Catalog | Supported fMRI neuroscience benchmarks |