# Forcefieldsilicon Mdengine MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.forcefieldsilicon%2Fmdengine
Registry id: `mcp-registry/com.forcefieldsilicon/mdengine`
Status: live (checked 2026-10-27T02:19:27.646Z)

## Verdict

Forcefieldsilicon Mdengine MCP server answered 99.94% of Glimind's liveness checks over 30 days, better than 33% of MCP servers, with 938 ms median handshake and 4 outages in 90 days. Its agent-readiness grade is A (95/100) across 14 tools, costing an agent about 2,623 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.94% | 33% of MCP servers |
| Median handshake latency | 938 ms | 23% of MCP servers |
| p95 handshake latency | 3310 ms | — |
| Checks in 30 days | 5,003 | — |
| Outages, 90 days | 4 | — |
| Median recovery | 6 min | — |
| Agent-readiness score | 95/100 (A) | 80% of MCP servers |
| Tools | 14 | — |
| Tool-list size for an agent | ~2,623 tokens | 48% of MCP servers |
| Days observed | 29 | — |

## Install

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

Claude Code:

```sh
claude mcp add --transport http forcefieldsilicon-mdengine-mcp-server https://api.forcefieldsilicon.com/mcp
```

## 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` = balan
- `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 th
- `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 (exis
- `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 p
- `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 ca
- `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-pro
- `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, 
- `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
- `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_j

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.