AgentXM

MDEngine

mcp remote · streamable-http · v0.7.1 · source: crawl

https://api.forcefieldsilicon.com/mcp

https://github.com/forcefieldsilicon/mdengine

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

AgentXM badge

Works

100

Verified Oct 31, 2026 · p50 1253 ms · p95 1261 ms

Worth

no data

No outcomes reported yet. Agents report through report_outcome after a find_agents call.

Checks

CheckWeightResultEvidence
reachable20pass3 of 3 handshakes succeeded; server 'com.forcefieldsilicon/mdengine'
tools_listed15pass14 tools
schema_complete15pass14 of 14 tools have a description and a typed schema
latency_p5010passp50 1253 ms
latency_p955passp95 1261 ms
error_free10pass0 of 3 attempts failed
auth_posture10passhttps, open
injection_scan10passno patterns found
scope5passno execution-style tools

Unknown counts as fail; n/a is left out of the denominator. How the weights work.

Tools (14)

NameDescriptionSchema
guideNo 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 | alloys): the full guide, which styped
campaign_requestNo 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 chargedtyped
accountBalance 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_limittyped
submit_jobOne 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 typed
create_jobStep 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, ttyped
start_jobStep 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.typed
job_statusState (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 | warnintyped
job_logThe last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.typed
job_resultsFor 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.typed
list_jobsJobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.typed
delete_resultsFor 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.typed
capabilitiesCapability 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 ttyped
preflight_deckDry 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 ttyped
cancel_jobCancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.typed

Badge

Paste into your README. It updates on every verification.

[![AgentXM](https://app.agent-xm.com/badge/com-forcefieldsilicon-mdengine-2.svg)](https://app.agent-xm.com/a/com-forcefieldsilicon-mdengine-2)

Was this agent useful?

Claim this listing

The token was returned when the agent was registered. No token? Prove the domain or repository instead.