vasp-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| --root | No | Limits the server to that folder. Repeat it for several folders. Without it, any folder the client names can be read. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_vasp_inputsB | Check the VASP inputs (INCAR, POSCAR, POTCAR, KPOINTS) in a folder for common mistakes. If the folder has no INCAR, every calculation folder below it is checked. Each finding has a rule ID, a severity (error, warning or info), the INCAR line, an explanation and the VASP wiki page it is based on. |
| summarize_vasp_runA | Summarize what happened in one VASP calculation folder. Reads OUTCAR (or OSZICAR), vasprun.xml and the job's standard output. Reports whether the job finished, whether the electronic and ionic loops converged, the final energies, the largest force on a free atom, pressure, Fermi level, magnetisation, MD temperatures, the band gap per spin channel, VASP warnings, known error messages, and a plain list of problems. |
| read_vasp_inputsC | The parsed inputs of one calculation: INCAR tags, structure, POTCAR datasets and k-points. |
| scan_vasp_projectA | List every VASP calculation folder below a path with a quick status. For each folder with an INCAR or OUTCAR: finished, incomplete or not run, the last energy(sigma->0) and whether a relaxation reached the required accuracy. Use summarize_vasp_run on a folder for the full picture. |
| list_vasp_lint_rulesA | All input checks with their severity and the VASP wiki page each is based on. |
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 5 tools
Each tool has a distinct role: input validation (check_vasp_inputs), input parsing (read_vasp_inputs), run summary (summarize_vasp_run), project scan (scan_vasp_project), and rule metadata (list_vasp_lint_rules). The only mild overlap is between check_vasp_inputs and read_vasp_inputs, but descriptions clearly separate validation from raw parsing.
All five tools follow the same verb_vasp_noun pattern (check_vasp_inputs, summarize_vasp_run, read_vasp_inputs, scan_vasp_project, list_vasp_lint_rules). The convention is uniform and predictable.
Five tools is well-scoped for a VASP analysis/validation server, with no redundant or filler tools. Each covers a clearly different stage of the workflow.
The surface covers input validation, input reading, run summarization, project scanning, and rule listing, which is solid lifecycle coverage for diagnostics. It lacks any write/fix or cross-run comparison operations, but those are outside the apparent read-only analysis scope.