colabfit-mcp
Officialby colabfit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| USER_ID | No | User ID for container (should match host user) | 1000 |
| GROUP_ID | No | Group ID for container (should match host user) | 1000 |
| VAL_SIZE | No | Number of validation configs (0 = auto 10% split) | 0 |
| TRAIN_SIZE | No | Number of training configs (0 = auto 90% split) | 0 |
| KLIFF_DTYPE | No | Training precision (float32 default; use float64 for higher accuracy) | float32 |
| KLIFF_BATCH_SIZE | No | Training batch size. Decrease if OOM. | 4 |
| COLABFIT_BASE_URL | No | ColabFit API base URL (used by search) | https://materials.colabfit.org |
| KLIFF_NUM_WORKERS | No | DataLoader worker processes. Keep at 0 to avoid CUDA fork deadlocks. | 0 |
| COLABFIT_AUTH_PASS | No | ColabFit API auth password (used by search) | mcp-secret |
| COLABFIT_AUTH_USER | No | ColabFit API auth username (used by search) | mcp-tool |
| COLABFIT_DATA_ROOT | No | Host-side bind-mount source directory. Inside the container the data root is always /home/mcpuser/colabfit. | ./colabfit_data |
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/colabfit/colabfit-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server