MDEngine

Install

Works with Claude Code, VS Code, Claude Desktop, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/forcefieldsilicon-com-mdengine

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

8 read · 4 write · 2 delete

Secrets

1 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Downloaded binary

Tools (14)

As the server listed them on Oct 25, 2026. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• accountAccount balance and pricingread-only

  Balance in USD (`balance_usd`), the part of it held by your unfinished jobs (`reserved_usd`, `held_jobs`) and what a new submit can use (`available_usd` = balance - reserved; a submit needs wall_limit_s x rate of it), 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, the key id of the API key in use, and `packs` (when the endpoint sells credit): [{id, name, usd, gpu_h, url}] to top up THIS key by appending ?client_reference_id=<key_id> to the pack url.

• campaign_requestStart a study: request a quoted campaign

  No key needed. Sends a study request to a person and returns a request_id, the tier that fits, the price band, what we still need from you, the next step and the claim scope. Nothing is run or charged. Call it after reading a guide.

• cancel_jobCancel jobcan change or delete data

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

• capabilitiesWhat the runner can doread-only

  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_jobCreate a job (returns upload URL)

  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_resultsDelete a job's files nowcan change or delete data

  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.

• guideStart here: guides by customer typeread-only

  No key needed. Without customer_type: the list of guides (one line each), the start page and how to get a key. With customer_type (mineral-processing | dark-proteins): the full guide, which says what to supply, what runs, what comes back and what it costs. With template (openmm-stability): the script text of that template, ready to save and submit.

• job_logJob log tailread-only

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

• job_resultsResults download URLread-only

  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_statusJob statusread-only

  State (created|uploaded|queued|launching|running|uploading|done|failed|cancelled), GPU, rate, billed seconds, cost so far, exit code, error, last thermo lines, and the post-run verdict: clean | warnings (a done run whose log shows QEq CG failures, lost atoms, a fix halt, or no end_marker line; counts in `warnings`).

• list_jobsList jobsread-only

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

• preflight_deckCheck a deck before spendingread-only

  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_jobStart an uploaded job

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

• submit_jobSubmit a deck (inline files) and start it

  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.

Signals

Stars

0

Forks

0

Open issues

0

Last commit

Oct 8, 2026 (23 days ago)

Last release

Sep 11, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

com.forcefieldsilicon/mdengine

Version

0.7.1

Auth

Bearer token

Packages

mcpb https://github.com/forcefieldsilicon/mdengine/releases/download/v0.7.1/mdengine-mcp-0.7.1-macos-arm64.mcpb

License

License unknown

Repository

github.com/forcefieldsilicon/mdengine

Website

forcefieldsilicon.com/mdengine

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql