MDEngine

com.forcefieldsilicon/mdengineVersion 0.7.1

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

Status

Responds119 msNov 14, 2026, 13:57 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 13:57 UTC
Latency: 119 ms
Remotes responding: 1 of 1
Sign-in: API key
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://api.forcefieldsilicon.com/mcpResponds119 msNov 14, 2026, 13:57 UTC

No sign-in

Claude Code

claude mcp add --transport http mdengine https://api.forcefieldsilicon.com/mcp --header 'Authorization: Bearer <YOUR_TOKEN>'

Replace <YOUR_TOKEN> before running.

Claude Desktop and claude.ai

Settings > Connectors > Add custom connector
Name: mdengine
Remote MCP server URL: https://api.forcefieldsilicon.com/mcp
This server expects the header Authorization.

Cursor

{
  "mcpServers": {
    "mdengine": {
      "url": "https://api.forcefieldsilicon.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Replace <YOUR_TOKEN> before running.

VS Code

code --add-mcp '{"name":"mdengine","type":"http","url":"https://api.forcefieldsilicon.com/mcp","headers":{"Authorization":"Bearer <YOUR_TOKEN>"}}'

Replace <YOUR_TOKEN> before running.

Streamable HTTP

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

Package only

This address cannot be turned into a client config.

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

14 tools

Tools of MDEngine
	Description		Read-only	Idempotent	Open world
`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.	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.	No	Yes	Yes	Yes
`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.	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.	No	No	No	Yes
`cancel_job`Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.	Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.	Yes	No	Yes	Yes
`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.	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.	No	Yes	Yes	Yes
`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.	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.	No	No	No	Yes
`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.	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.	Yes	No	Yes	Yes
`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 \| alloys): 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.	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 \| alloys): 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.	No	Yes	Yes	Yes
`job_log`The last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.	The last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.	No	Yes	Yes	Yes
`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.	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.	No	Yes	Yes	Yes
`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`).	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`).	No	Yes	Yes	Yes
`list_jobs`Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.	Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.	No	Yes	Yes	Yes
`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.	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.	No	Yes	Yes	Yes
`start_job`Step 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.	Step 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.	No	No	No	Yes
`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.	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.	No	No	No	Yes

Details

Registry status: Active
Published: Sep 11, 2026
Updated: Sep 11, 2026
Website: https://forcefieldsilicon.com/mdengine⁠ (opens in a new tab)
Repository: https://github.com/forcefieldsilicon/mdengine⁠ (opens in a new tab)
Categories (suggested): Marketing and SEOSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing