Goldilocks MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Goldilocks MCP ServerEstimate k-point spacing for BaGa4.cif at 0.95 confidence with ALIGNN model."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Goldilocks MCP server
Provides k-point generation tools for Quantum ESPRESSO with SSSP1.3 PBEsol efficiency version of pseudo-potentials
Tools exposed:
estimate_kpoint_distance
Requires specification path to the structure file, confidence level (models are trained for levels 0.85,0.9, and 0.95), and the model (ALIGNN or RF)
Example prompt: "Can you please generate k-points spacing for structure 'path/to/BaGa4.cif', confidence level 0.95 with ALIGNN model?"
Outputs the predicted k-spacing, and the confidence interval
generate_kpoint_grid
Requires specification path to the structure file, confidence level (models are trained for levels 0.85,0.9, and 0.95), and the model (ALIGNN or RF)
Example prompt: "Can you please generate k-points grid for structure 'path/to/BaGa4.cif', confidence level 0.95 with ALIGNN model?"
Outputs the predicted kmesh, generated using the lower bound of k-spacing interval (to make sure that the probability that predicted value is in agreement with confidence level)
Related MCP server: Materials Project MCP
Installing MCP-server locally
Install uv (https://docs.astral.sh/uv/getting-started/installation/)
Clone repository
git clone https://github.com/stfc/goldilocks-mcp.git
cd goldilocks-mcpCreate virtual environment and install dependencies
uv venv --python 3.11
source .venv/bin/activate
uv pip install -e .Install pytorch-geometric (can't be installed from pyproject.toml but is required). See details https://pytorch-geometric.readthedocs.io/en/latest/install/installation.html
uv pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.8.0+cpu.html
uv pip install torch_geometricAdding mcp to Claude Desktop
To add goldilocks-mcp to Claude Desktop:
Open or create the Claude Desktop configuration file:
macOS/Linux:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows: See instructions at https://modelcontextprotocol.io/docs/develop/build-server
If the file doesn't exist, create it with the content from
claude_desktop_config.json. If it already exists, merge thegoldilocks-mcpentry into the existingmcpServersobject.Important: Update the path in the config file. Replace
"absolute/path/to/goldilocks-mcp/goldilocks_mcp/"with the actual absolute path to thegoldilocks_mcpdirectory in your cloned repository.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
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/stfc/goldilocks-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server