# MDEngine

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

- name: com.forcefieldsilicon/mdengine
- version: 0.7.1
- connection class: R1 (autonomous)
- trust: 96/100
- quality: 75/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.forcefieldsilicon%2Fmdengine
- tools: https://api.protogrid.dev/v1/servers/com.forcefieldsilicon%2Fmdengine/tools

**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.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "mdengine": {
      "type": "http",
      "url": "https://api.forcefieldsilicon.com/mcp",
      "headers": {
        "Authorization": "Bearer ${MDENGINE_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${MDENGINE_TOKEN}`.

## Trust

- hygiene: 95
- liveness: 100
- freshness: 85
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-100% ~updated-39d-ago -unpinned-packages(1)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 14 of 14 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,657 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 6 tool changes in 30 days
- fail `stability.rug_pull`: 1 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 14, about 2,657 tokens to load them all
- tool set hash: cb0640c5993b11ca5b4bbb8a1e066b08
- tools last changed: 2026-10-08T06:46:52.872Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.forcefieldsilicon/mdengine.svg)](https://protogrid.dev/servers/com.forcefieldsilicon/mdengine)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-08 `campaign_request` added
  - 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.
- 2026-10-08 `guide` added
  - 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.
- 2026-10-01 `job_status` changed (description) **meaning 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: 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`).
- 2026-10-01 `create_job` changed (inputSchema)
- 2026-10-01 `submit_job` changed (inputSchema)
- 2026-10-01 `account` changed (description)
  - 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: 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.

Full history: https://api.protogrid.dev/v1/servers/com.forcefieldsilicon%2Fmdengine/changes

## Remotes

- https://api.forcefieldsilicon.com/mcp (streamable-http, auth api_key ${MDENGINE_TOKEN}, reachable true, uptime30d 1)

## Packages

- mcpb https://github.com/forcefieldsilicon/mdengine/releases/download/v0.7.1/mdengine-mcp-0.7.1-macos-arm64.mcpb

## Tools (14)

- `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-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_job`: Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.
- `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 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_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.
- `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 script text of that template, ready to save and submit.
- `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.
- `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; counts in `warnings`).
- `list_jobs`: Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.
- `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 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.