An agent can connect on its own if it already holds MDENGINE_TOKEN.Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.
tools.schemasevery tool has an object input schema
pass
tools.annotations14 of 14 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 2,657 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump
stability25 · weight 15
warn
stability.changes6 tool changes in 30 days
fail
stability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting them
dependenciesn/a · weight 15
n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package
14 tools, about 2,657 tokens to load them all · tool set cb0640c5993b · tools last changed 2026-10-08 · checked 2026-10-19 10:52 UTC
Tool changes
campaign_requestadded
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.
guideadded
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_statuschangeddescriptionmeaning changed
before
State (created|uploaded|queued|launching|running|uploading|done|failed|cancelled), GPU, rate, billed seconds, cost so far, exit code, error, last thermo lines.
after · 48% of words in common
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`).
create_jobchangedinput schema
submit_jobchangedinput schema
accountchangeddescription
before
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.
after · 54% of words in common
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.
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_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.
cancel_jobdestructive
Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.
capabilitiesread-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_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.
delete_resultsdestructive
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.
guideread-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_logread-only
The last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.
job_resultsread-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_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_jobsread-only
Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.
preflight_deckread-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_job
Step 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.
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. The deck is executed as a program on an isolated GPU pod.
protogrid