mle_kit_mcp
by IlyaGusev
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Default server port. | 5057 |
| GPU_TYPE | No | GPU type for remote instances. | RTX_3090 |
| DISK_SPACE | No | Disk space in GB for remote instances. | 300 |
| VAST_AI_KEY | No | Optional but required to launch new vast.ai instances. | |
| WORKSPACE_DIR | Yes | Absolute path to your workspace directory. | |
| EXISTING_SSH_KEY | No | Path to an SSH private key to use with the existing instance. | |
| OPENROUTER_API_KEY | No | Optional but required for OpenRouter proxy tools. | |
| OPENROUTER_BASE_URL | No | Base URL for OpenRouter. | https://openrouter.ai/api/v1 |
| EXISTING_INSTANCE_ID | No | Use an existing vast.ai instance ID instead of creating a new one. |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/IlyaGusev/mle_kit_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server