com.forcefieldsilicon/mdengine

up checked 2026-11-11T04:38:13.751Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

MDEngine

Publisher-provided description

MD workbench for agents: 13 analysis tools, renders, hosted GPU runs; LAMMPS + OpenMM.

Summary by lookupd

Runs hosted GPU molecular dynamics jobs (LAMMPS, OpenMM), tracks job status and logs, and retrieves results and billing info.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http mdengine https://api.forcefieldsilicon.com/mcp

Codex, remote (streamable-http)

codex mcp add mdengine --url https://api.forcefieldsilicon.com/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "mdengine": {
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (14 tools)

Publisher-provided text

guide 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-pro
campaign_request 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 th
account 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` = balan
submit_job 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_j
create_job 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 p
start_job Step 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.
job_status State (created|uploaded|queued|launching|running|uploading|done|failed|cancelled), GPU, rate, billed seconds, cost so far, exit code, error, last thermo lines,
job_log The last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.
job_results 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
list_jobs Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.
delete_results 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 ca
capabilities Capability manifest of the hosted runners: LAMMPS version, installed packages, and every style by category with gpu=true (KOKKOS-accelerated) or gpu=false (exis
preflight_deck 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
cancel_job Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.

Details

Version: 0.7.1
Transports: streamable-http, stdio
Uptime (7 days): 100%
Median latency: 686 ms
First indexed: 2026-11-01T08:54:06.155Z
Last seen in registry: 2026-11-01T08:54:06.184Z
Repository: https://github.com/forcefieldsilicon/mdengine
Website: https://forcefieldsilicon.com/mdengine

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.forcefieldsilicon/mdengine.svg)](https://lookupd.com/servers/com.forcefieldsilicon/mdengine)

62033 servers
Last crawl: 2026-11-11T15:38:39.561Z
API base: https://api.lookupd.com
MCP URL: https://api.lookupd.com/mcp