Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

MDEngine

REMOTE · API.FORCEFIELDSILICON.COM · 2 COMPONENTS · SCANNED SEP 20

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

+3 this week 73 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability77
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1449 tokens (~120/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management43
  • Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the MDEngine MCP server?

MDEngine is a hosted endpoint at https://api.forcefieldsilicon.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.forcefieldsilicon.com

# add to Claude Code
claude mcp add --transport http com-forcefieldsilicon-mdengine 'https://api.forcefieldsilicon.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-forcefieldsilicon-mdengine": {
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-forcefieldsilicon-mdengine": {
      "type": "http",
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-forcefieldsilicon-mdengine]
url = "https://api.forcefieldsilicon.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-forcefieldsilicon-mdengine": {
      "type": "remote",
      "url": "https://api.forcefieldsilicon.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-forcefieldsilicon-mdengine --url 'https://api.forcefieldsilicon.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-forcefieldsilicon-mdengine:
    url: "https://api.forcefieldsilicon.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-forcefieldsilicon-mdengine": {
      "Transport": "http",
      "Url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-forcefieldsilicon-mdengine -t streamable-http -u 'https://api.forcefieldsilicon.com/mcp'
// mcp.json
{
  "mcpServers": {
    "com-forcefieldsilicon-mdengine": {
      "type": "http",
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 0
    • Tool “account” rewrote its description, which is the text the model reads security
    • “create_job” reworded the description of “gpu” cosmetic
    • “submit_job” reworded the description of “gpu” cosmetic
    • Tool “account” changed its title: Account balance and rates → Account balance and pricing cosmetic
  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 0
    • Server version: 0.5.0 → 0.6.0 functional
  • 8 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • New tool “delete_results”, which the server declares destructive security
    • Tool “list_jobs” rewrote its description, which is the text the model reads security
    • Tool “submit_job” rewrote its description, which is the text the model reads security
    • Schema quality: 1038 → 1410 functional
    • Stability: unverified → 0.03 functional
    • Destructive annotations: pass → 100 functional
    • Server version: 0.2.0 → 0.5.0 functional
    • New tool “capabilities” functional
    • New tool “preflight_deck” functional
    • “list_jobs” added an optional parameter “full” cosmetic
    • “create_job” reworded the description of “gpu” cosmetic
    • “create_job” reworded the description of “runner” cosmetic
    • “list_jobs” reworded the description of “limit” cosmetic
    • “submit_job” reworded the description of “gpu” cosmetic
    • “submit_job” reworded the description of “runner” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://api.forcefieldsilicon.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.forcefieldsilicon.com CN=YE2,O=Let's Encrypt,C=US 6 Sept 2026 5 Dec 2026 ECDSA 256 ECDSA-SHA384 5bd789af2e29cedb1ec75ffc2205298d065
SANs: api.forcefieldsilicon.com
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.forcefieldsilicon.com. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
forcefieldsilicon.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.forcefieldsilicon.com/mcp Verified 200
http (plaintext) http://api.forcefieldsilicon.com/mcp HTTPS enforced 308 https://api.forcefieldsilicon.com/mcp
MCP tools · 12 exposed · ~1,367 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
account ~67

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

cancel_job ~56

Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.

NameTypeReqDescription
idstringyesJob id, e.g. MDJOB-20260907-3F200C

No output schema declared.

No examples provided.

capabilities ~119

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.

NameTypeReqDescription
fullbooleanInclude the full style table (large)
runnerstringlammps | openmm; omit for all

No output schema declared.

No examples provided.

create_job ~253

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.

NameTypeReqDescription
estimate_sintegerYour runtime guess in seconds; only used for the balance pre-check (min 900 s at the rate)
gpustringGPU class; call account for the offered classes and how jobs are priced. Default any = cheapest available
inputstringyesRelative path of the LAMMPS (or runner) input script inside the deck, e.g. in.lmp
labelstringFree text <= 120 chars shown in job lists
launchstringLaunch template; omit for the default KOKKOS/CUDA LAMMPS command line
runnerstringRunner flavour: lammps (default) or openmm (beta)
wall_limit_sintegerHard cap in seconds (default 14400, max 86400); the job fails at the cap and is billed to it

No output schema declared.

No examples provided.

delete_results ~69

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.

NameTypeReqDescription
idstringyesJob id, e.g. MDJOB-20260907-3F200C

No output schema declared.

No examples provided.

job_log ~61

The last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.

NameTypeReqDescription
idstringyesJob id, e.g. MDJOB-20260907-3F200C

No output schema declared.

No examples provided.

job_results ~76

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.

NameTypeReqDescription
idstringyesJob id, e.g. MDJOB-20260907-3F200C

No output schema declared.

No examples provided.

job_status ~75

State (created|uploaded|queued|launching|running|uploading|done|failed|cancelled), GPU, rate, billed seconds, cost so far, exit code, error, last thermo lines.

NameTypeReqDescription
idstringyesJob id, e.g. MDJOB-20260907-3F200C

No output schema declared.

No examples provided.

list_jobs ~74

Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.

NameTypeReqDescription
fullbooleanReturn the complete status object per job (default false)
limitinteger1..200, default 20

No output schema declared.

No examples provided.

preflight_deck ~144

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.

NameTypeReqDescription
filesobjectyesDeck contents {path: text}, must include `input`
inputstringyesRelative path of the LAMMPS (or runner) input script inside the deck, e.g. in.lmp

No output schema declared.

No examples provided.

start_job ~60

Step 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.

NameTypeReqDescription
idstringyesJob id, e.g. MDJOB-20260907-3F200C

No output schema declared.

No examples provided.

submit_job ~313

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.

NameTypeReqDescription
estimate_sintegerYour runtime guess in seconds; only used for the balance pre-check (min 900 s at the rate)
filesobjectyesDeck contents: {"in.lmp": "...", "data.al": "..."}; paths relative, no '..'; must include `input`
gpustringGPU class; call account for the offered classes and how jobs are priced. Default any = cheapest available
inputstringyesRelative path of the LAMMPS (or runner) input script inside the deck, e.g. in.lmp
labelstringFree text <= 120 chars shown in job lists
launchstringLaunch template; omit for the default KOKKOS/CUDA LAMMPS command line
runnerstringRunner flavour: lammps (default) or openmm (beta)
wall_limit_sintegerHard cap in seconds (default 14400, max 86400); the job fails at the cap and is billed to it

No output schema declared.

No examples provided.

Common questions

What is the MDEngine MCP server?

MDEngine is an MCP server listed in the public MCP registry as com.forcefieldsilicon/mdengine. MD workbench for agents: 13 analysis tools, renders, hosted GPU runs; LAMMPS + OpenMM. This page covers its hosted endpoint (https://api.forcefieldsilicon.com/mcp).

Is the MDEngine MCP server safe to use?

MDEngine scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the MDEngine MCP server expose?

MDEngine exposes 12 tools: account, submit_job, create_job, start_job, job_status, and 7 more. Their descriptions and schemas cost roughly 1,367 tokens of context every time the server is loaded.

Does the MDEngine MCP server require authentication?

No. We connected to MDEngine without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the MDEngine MCP server still maintained?

MDEngine is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.