wyoloservice2_mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEURALFORGE_API_URL | Yes | The Base URL of the NeuralForgeAI cluster API (e.g., http://192.168.10.252:23442) |
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 |
|---|---|
| set_cluster_credentialsA | Save the cluster IP and Samba CIFS credentials to a local configuration file. The agent should call this tool when the user provides the cluster IP and credentials. |
| get_cluster_statusA | Get the overall status of the NeuralForgeAI cluster, including health metrics, active celery workers (invokers), and the current tasks queue. |
| get_study_detailsA | Get detailed telemetry and status of a specific YOLO training study. Returns progress, active invoker, and current trial metrics. IMPORTANT WORKFLOW FOR AGENTS: When the user asks 'how is my training going?' (or similar) without providing a study_id:
|
| cancel_studyA | Cancel a running training study by its ID. This will stop the active trials and terminate the executor containers. |
| generate_training_yamlA | Generate a NeuralForgeAI training YAML configuration file and save it to disk. This allows the user to inspect the file before launching the training. Returns the absolute path to the generated YAML file. |
| launch_trainingA | Submit a locally saved YOLO training YAML configuration to the NeuralForgeAI cluster.
Use this after the user has reviewed and approved the YAML file generated by |
| check_dataset_pathB | Verify if a dataset path exists on the remote Samba share by spinning up a lightweight Docker container. |
| validate_dataset_advancedB | Validates a YOLO dataset structure by running an inspection script inside a Docker container connected to the remote CIFS share. Supports detect/segment (yaml) and classify (directory). |
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
Each tool has a clearly distinct purpose: canceling, checking paths, generating YAML, cluster status, study details, launching, credentials, and dataset validation. No overlapping functionality.
All tools use snake_case with a consistent verb_noun pattern (e.g., cancel_study, generate_training_yaml). There are no naming convention conflicts.
8 tools is appropriate for the server's scope—covering credential setup, dataset validation, YAML generation, training launch, monitoring, and cancellation. No unnecessary tools.
The toolset covers the core training lifecycle, but lacks a tool to list existing studies or modify credentials after setup. The workflow instructs agents to find study IDs from local YAML files, which is a reasonable workaround.