AI & Machine Learning

forcefieldsilicon.com

Manages GPU compute jobs by submitting, uploading, and monitoring job statuses with account balance and rate information.

1 endpoint12 known toolsFirst detected September 7, 2026Last detected September 7, 2026

ENDPOINT 1

https://api.forcefieldsilicon.com/mcp

No auth detected

MCP server metadata

Name: com.forcefieldsilicon/mdengine
Version: 0.4.0

Capabilities

tools

Server instructions

Hosted GPU runs for MDEngine. Every tool except this handshake needs a credential: sign in through OAuth (paste your API key once) or send `Authorization: Bearer mde_...` (key from a credit pack at https://forcefieldsilicon.com/mdengine). Typical flow: account -> submit_job (inline deck) -> job_status/job_log until done -> job_results.

Known tools 12

account

Balance in USD, the per-GPU hourly rate table, and the key id of the API key in use.

Inferred read-only

submit_job

One call: create a hosted GPU job, upload the deck given INLINE as {relative_path: text}, and queue it.

Potential side effects

create_job

Step 1 of the two-step path for big decks: validates the spec, reserves a job id, returns a presigned upload_url.

Inferred read-only

start_job

Step 2: queue a job whose deck tarball has been uploaded.

Inferred read-only

job_status

Inferred read-only

job_log

The last <= 20 thermo/log lines the running pod reported (30 s heartbeat).

Inferred read-only

job_results

For a done/failed job: a presigned download_url (valid ~7 days) for the results tarball (work/, log.

Inferred read-only

list_jobs

Jobs of this API key, newest first.

Inferred read-only

delete_results

For a finished job: delete its deck and results tarballs immediately instead of at the automatic 30-day purge.

Potential side effects

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).

Inferred read-only

preflight_deck

Dry run of the check submit_job performs: which styles the deck asks for are MISSING on the hosted LAMMPS image (the run would exit at startup), which are CPU-only, and whether its pair style will use the GPU at all.

Inferred read-only

cancel_job

Cancel a job that is not finished.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.com-forcefieldsilicon-mdengine]
url = "https://api.forcefieldsilicon.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "com-forcefieldsilicon-mdengine": {
      "type": "http",
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: com-forcefieldsilicon-mdengine
Remote MCP URL: https://api.forcefieldsilicon.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "com-forcefieldsilicon-mdengine": {
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "com-forcefieldsilicon-mdengine": {
      "type": "http",
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "com-forcefieldsilicon-mdengine",
  "transport": "streamable-http",
  "url": "https://api.forcefieldsilicon.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.