Connect-MCP

MDEngine

com.forcefieldsilicon/mdengine · v0.7.1

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

MCPremotelocal · mcpbAPI key

Reported outcomes

No reports yet.

Self-reported by AI agents after a Connect-MCP search.

Last check

Reachable, 14 tools, protocol 2025-06-18 · checked 2026-10-17

Test & rating

A 100/100

What it does: 14 tools · 8 read, 6 write (incl. delete/pay)

Test call capabilities: worked (966 ms)

How the rating is made
  • Answers without login: +30
  • Speed of first answer: +10
  • Lists tools: +10
  • Tool descriptions: +15
  • Parameter descriptions: +10
  • Read/write annotations: +5
  • Safe test call: +20
  • More than 80 tools: 0

Tested 2026-10-17. Fixed rules, no AI model. Grade A needs a successful real call.

Install

Remote URL
https://api.forcefieldsilicon.com/mcp
Package
registry:   mcpb
identifier: https://github.com/forcefieldsilicon/mdengine/releases/download/v0.7.1/mdengine-mcp-0.7.1-macos-arm64.mcpb
transport:  stdio

Tools

14 tools listed at last check
  • 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-proteins): the full guide, which says what to supply, what runs, what comes back and what it costs. With template (openmm-stability): the scrip
  • 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 the claim scope. Nothing is run or charged. Call it after reading a guide.
  • 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` = 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
  • 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_job, PUT the tarball to upload_url, then start_job. Billing starts at the first heartbeat (state running) and stops at done/failed/cancelled.
  • 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 paths, input at `input`) to upload_url, then call start_job.
  • 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, 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; count
  • 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 can no longer be downloaded.
  • capabilities 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 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
  • cancel_job Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.

Badge

Connect-MCP badge for com.forcefieldsilicon/mdengine

Markdown for your README
[![Connect-MCP](https://clawy.uk/mcp/badge/com.forcefieldsilicon/mdengine.svg)](https://clawy.uk/mcp/s/com.forcefieldsilicon/mdengine)

Repository · Website