MDEngine MCP server

• accountFree

  Balance in USD, how jobs are priced (`pricing.mode` job = the deck's own work in atom-steps at per-class prices, capped at wall_limit_s x rate; metered = per second of pod time), the rate table, and the key id of the API key in use.

• cancel_jobwrite actionFree

  Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.

• capabilitiesFree

  Capability manifest of the hosted runners: LAMMPS version, installed packages, and every style by category with gpu=true (KOKKOS-accelerated) or gpu=false (exists, but runs on the pod's CPU cores at the GPU rate). Default = compact summary; runner=lammps&full=true returns the whole style table. Use preflight_deck to check a specific deck.

• create_jobwrite actionFree

  Step 1 of the two-step path for big decks: validates the spec, reserves a job id, returns a presigned upload_url. PUT the deck as a .tar.gz (<= 2 GB, relative paths, input at `input`) to upload_url, then call start_job.

• delete_resultswrite actionFree

  For a finished job: delete its deck and results tarballs immediately instead of at the automatic 30-day purge. Metadata and billing records are kept; results can no longer be downloaded.

• job_logFree

  The last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.

• job_resultsFree

  For a done/failed job: a presigned download_url (valid ~7 days) for the results tarball (work/, log.lammps, exitcode). Results are deleted 30 days after the run.

• job_statusFree

  State (created|uploaded|queued|launching|running|uploading|done|failed|cancelled), GPU, rate, billed seconds, cost so far, exit code, error, last thermo lines.

• list_jobsFree

  Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.

• preflight_deckFree

  Dry run of the check submit_job performs: which styles the deck asks for are MISSING on every hosted LAMMPS image (the run would exit at startup), which are CPU-only, whether its pair style will use the GPU at all, and which image (`runner`) the job will be routed to — decks needing packages beyond the fast default image run on lammps-full automatically. Nothing is created or billed.

• start_jobFree

  Step 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.

• submit_jobwrite actionFree

  One call: create a hosted GPU job, upload the deck given INLINE as {relative_path: text}, and queue it. Total inline size <= 8 MB; for larger decks use create_job, PUT the tarball to upload_url, then start_job. Billing starts at the first heartbeat (state running) and stops at done/failed/cancelled. The deck is executed as a program on an isolated GPU pod.

• –Code scanpackage could not be scannedn/a
• Live reliabilityremote reachable in 1857ms20/20
• Tool poisoning12 tool descriptions checked15/15
• Auth qualityAPI key sent as a header8/15
• Maintenancelast push 8 days ago15/15
• Maintainer identityregistry namespace matches repository owner; website matches verified namespace9/10

MDEngine: common questions

Is MDEngine MCP server safe?

Yes, by our scan: it is graded A (89/100). Read the MDEngine safety report

How do I install MDEngine?

It runs remotely at api.forcefieldsilicon.com. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.

Does MDEngine need an API key?

Yes. The registry entry asks for Authorization.

Is MDEngine maintained?

The last commit was 9 days ago (2026-09-11). The latest release is v0.7.1.

Is MDEngine up?

100% of our last 6 checks got an answer. We check remote servers about four times a day.