MCP Server
MDEngine
com.forcefieldsilicon/mdengine
What this MCP does
Runs hosted GPU molecular-dynamics workloads using LAMMPS or OpenMM, with deck validation, job management, logs, billing, and downloadable results.
Capabilities
Tools
12
tools
account
Account balance and pricing
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.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {}}
cancel_job
Cancel job
Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.
Destructive
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Job id, e.g. MDJOB-20260907-3F200C'}}}
capabilities
What the runner can do
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.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'full': {'type': 'boolean', 'description': 'Include the full style table (large)'}, 'runner': {'type': 'string', 'description': 'lammps | openmm; omit for all'}}}
create_job
Create 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.
Open world
Input schema
{'type': 'object', 'required': ['input'], 'properties': {'gpu': {'type': 'string', 'description': 'GPU class; call account for the offered classes and how jobs are priced. Default any = cheapest available'}, 'input': {'type': 'string', 'description': 'Relative path of the LAMMPS (or runner) input script inside the deck, e.g. in.lmp'}, 'label': {'type': 'string', 'description': 'Free text <= 120 chars shown in job lists'}, 'launch': {'type': 'string', 'description': 'Launch template; omit for the default KOKKOS/CUDA LAMMPS command line'}, 'runner': {'type': 'string', 'description': 'Runner flavour: lammps (default) or openmm (beta)'}, 'estimate_s': {'type': 'integer', 'description': 'Your runtime guess in seconds; only used for the balance pre-check (min 900 s at the rate)'}, 'wall_limit_s': {'type': 'integer', 'description': 'Hard cap in seconds (default 14400, max 86400); the job fails at the cap and is billed to it'}}}
delete_results
Delete a job's files now
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.
Destructive
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Job id, e.g. MDJOB-20260907-3F200C'}}}
job_log
Job log tail
The last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Job id, e.g. MDJOB-20260907-3F200C'}}}
job_results
Results download URL
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.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Job id, e.g. MDJOB-20260907-3F200C'}}}
job_status
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.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Job id, e.g. MDJOB-20260907-3F200C'}}}
list_jobs
List jobs
Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'full': {'type': 'boolean', 'description': 'Return the complete status object per job (default false)'}, 'limit': {'type': 'integer', 'description': '1..200, default 20'}}}
preflight_deck
Check a deck before spending
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.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['input', 'files'], 'properties': {'files': {'type': 'object', 'description': 'Deck contents {path: text}, must include `input`', 'additionalProperties': {'type': 'string'}}, 'input': {'type': 'string', 'description': 'Relative path of the LAMMPS (or runner) input script inside the deck, e.g. in.lmp'}}}
start_job
Start 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.
Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Job id, e.g. MDJOB-20260907-3F200C'}}}
submit_job
Submit 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.
Open world
Input schema
{'type': 'object', 'required': ['input', 'files'], 'properties': {'gpu': {'type': 'string', 'description': 'GPU class; call account for the offered classes and how jobs are priced. Default any = cheapest available'}, 'files': {'type': 'object', 'description': 'Deck contents: {"in.lmp": "...", "data.al": "..."}; paths relative, no \'..\'; must include `input`', 'additionalProperties': {'type': 'string'}}, 'input': {'type': 'string', 'description': 'Relative path of the LAMMPS (or runner) input script inside the deck, e.g. in.lmp'}, 'label': {'type': 'string', 'description': 'Free text <= 120 chars shown in job lists'}, 'launch': {'type': 'string', 'description': 'Launch template; omit for the default KOKKOS/CUDA LAMMPS command line'}, 'runner': {'type': 'string', 'description': 'Runner flavour: lammps (default) or openmm (beta)'}, 'estimate_s': {'type': 'integer', 'description': 'Your runtime guess in seconds; only used for the balance pre-check (min 900 s at the rate)'}, 'wall_limit_s': {'type': 'integer', 'description': 'Hard cap in seconds (default 14400, max 86400); the job fails at the cap and is billed to it'}}}
History
Recent tool changes
Added
cancel_job
Sept. 17, 2026, 12:34 p.m.
Added
preflight_deck
Sept. 17, 2026, 12:34 p.m.
Added
capabilities
Sept. 17, 2026, 12:34 p.m.
Added
delete_results
Sept. 17, 2026, 12:34 p.m.
Added
list_jobs
Sept. 17, 2026, 12:34 p.m.
Added
job_results
Sept. 17, 2026, 12:34 p.m.
Added
job_log
Sept. 17, 2026, 12:34 p.m.
Added
job_status
Sept. 17, 2026, 12:34 p.m.
Added
start_job
Sept. 17, 2026, 12:34 p.m.
Added
create_job
Sept. 17, 2026, 12:34 p.m.
Added
submit_job
Sept. 17, 2026, 12:34 p.m.
Added
account
Sept. 17, 2026, 12:34 p.m.
Discover
Similar MCP servers
Hydrata - ANUGA Flood Simulation
com.hydrata/hydrata-mcp-server
Creates and manages ANUGA flood simulation projects, imports terrain and geospatial inputs, builds scenarios, runs simulations, a…
agent-compute-ledger
io.github.jdhart81/agent-compute-ledger
Records and verifies agent compute energy and carbon usage in tamper-evident ledgers, validates Landauer-limit claims, and produc…
Cloud World Model
ai.cloudworldmodel/cloud-world-model
Creates and runs temporary cloud architecture simulations with traffic, failures, recovery, performance metrics, and cost estimat…
green-router
io.github.jdhart81/green-router
Estimates compute energy and carbon footprints, ranks compute backends by emissions, and issues verifiable certificates tied to o…
Zhijiangyun Cloud (智匠云)
cloud.artibot/zhijiangyun
Supports GPU training, inference, benchmarking, and robot data collection for embodied-AI systems.
BorealHost
ai.borealhost/mcp
Provides web hosting and infrastructure management, including site deployment, DNS, domains, containers, compute, backups, cachin…
Clink Forge
com.clinkforge/clink-forge
Provides pay-per-call access to attested government datasets, primarily CDC and HHS health data plus EPA air-quality observations.
workbench
com.seqbench/workbench
Provides computational molecular biology tools for DNA, RNA, and protein analysis, cloning, PCR, CRISPR, oligonucleotide design, …