An MCP server that provides access to the ColabFit database
An MCP server that provides access to the ColabFit database
This is a Model Context Protocol (MCP) server that gives AI assistants the ability to: - Search and download scientific datasets from ColabFit - Train MACE interatomic potentials on your local hardware (GPU or CPU) - Run energy/forces calculations and validate models with OpenKIM test drivers
The server publishes 10 tools. What each one is for:
search_datasets — Search ColabFit database by text, elements, properties, softwarecheck_local_datasets — Scan local data directory for downloaded datasets, filter by elements/propertiesdownload_dataset — Download a dataset from HuggingFace via KLIFFtrain_mace — Train a MACE-style KLAY model from scratch using KLIFFuse_model — Run energy/forces/relax calculations with a trained KLAY model, or generate a Python snippetcheck_status — Check GPU, packages, disk, existing models and datasetslist_test_drivers — List available kimvv test drivers, optionally filtered by property keywordrun_test_driver — Run a kimvv test driver against a trained KLAY model; saves structures.extxyz + results.json in a timestamped subdirectory; supports multiplecheck_test_driver_result — Check status of an async test driver job and return inline results when completeRequirements — The Requirements tool exposed by this serversearch_datasets — Search ColabFit database by text, elements, properties, softwarecheck_local_datasets — Scan local data directory for downloaded datasets, filter by elements/propertiesdownload_dataset — Download a dataset from HuggingFace via KLIFFtrain_mace — Train a MACE-style KLAY model from scratch using KLIFFuse_model — Run energy/forces/relax calculations with a trained KLAY model, or generate a Python snippetcheck_status — Check GPU, packages, disk, existing models and datasetslist_test_drivers — List available kimvv test drivers, optionally filtered by property keywordrun_test_driver — Run a kimvv test driver against a trained KLAY model; saves structures.extxyz + results.json in a timestamped subdirectory; supports multiple structures per call with optional repeat for supercell sizing and async_mode fcheck_test_driver_result — Check status of an async test driver job and return inline results when completeCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| search_datasets | Search ColabFit database by text, elements, properties, software |
| check_local_datasets | Scan local data directory for downloaded datasets, filter by elements/properties |
| download_dataset | Download a dataset from HuggingFace via KLIFF |
| train_mace | Train a MACE-style KLAY model from scratch using KLIFF |
| use_model | Run energy/forces/relax calculations with a trained KLAY model, or generate a Python snippet |
| check_status | Check GPU, packages, disk, existing models and datasets |
| list_test_drivers | List available kimvv test drivers, optionally filtered by property keyword |
| run_test_driver | Run a kimvv test driver against a trained KLAY model; saves structures.extxyz + results.json in a timestamped subdirectory; supports multiple structures per call with optional repeat for supercell sizing and async_mode f |
| check_test_driver_result | Check status of an async test driver job and return inline results when complete |
{
"mcpServers": {
"colabfit": {
"command": "uvx",
"args": ["mcp-cli"],
"env": {
"COLABFIT_DATA_ROOT": "your-value",
"USER_ID": "your-value",
"GROUP_ID": "your-value",
"COLABFIT_BASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| COLABFIT_DATA_ROOT | Configuration value read at startup. | Optional |
| USER_ID | Configuration value read at startup. | Optional |
| GROUP_ID | Configuration value read at startup. | Optional |
| COLABFIT_BASE_URL | Endpoint or connection string the server talks to. | Yes |
Inspect PostgreSQL schemas and run read-only queries with the archived MCP reference server. Review its maintenance status before choosing it.
Use the Supabase MCP server to inspect database schemas, query project data and retrieve docs through a project-scoped connection.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Connects Elasticsearch data to any Model Context Protocol (MCP) Client, enabling natural language interaction.