Skip to content

MDEngine MCP server

com.forcefieldsilicon/mdengineforcefieldsilicon.comstreamable-httpv0.7.1Scanned

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

14 tools: 2 can delete or cancel things, 9 change things and 3 only read.

Tools: 2 delete, 0 irreversible, 9 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 14
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the MDEngine MCP server can do

The MDEngine MCP server is published by forcefieldsilicon.com, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (2 tools: delete_results and cancel_job) and create or change data (9 tools: guide, campaign_request, account, submit_job and 5 more). 3 tools only read.

14 tools bring in text other people can write (guide, campaign_request, account and 11 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 10, 2026, version 0.7.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

14 tools

Deletes or cancels 2Claude Code: deny
  • cancel_jobCancel a job that is not finished.Reads text others writeNo findings

    Why it is in this group

    • The name "cancel_job" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
    • title: Cancel job
  • delete_resultsFor a finished job: delete its deck and results tarballs immediately instead of at the automatic 30-day purge.Reads text others writeNo findings

    Why it is in this group

    • The name "delete_results" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
    • title: Delete a job's files now
Changes things 9Claude Code: ask
  • accountBalance 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 sub…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Account balance and pricing
  • campaign_requestNo key needed.Reads text others writeNo findings

    Why it is in this group

    • The name "campaign_request" says "request": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Start a study: request a quoted campaign
  • capabilitiesCapability 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 …Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: What the runner can do
  • create_jobStep 1 of the two-step path for big decks: validates the spec, reserves a job id, returns a presigned upload_url.Reads text others writeNo findings

    Why it is in this group

    • The name "create_job" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Create a job (returns upload URL)
  • guideNo key needed.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Start here: guides by customer type
  • job_resultsFor a done/failed job: a presigned download_url (valid ~7 days) for the results tarball (work/, log.lammps, exitcode).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Results download URL
  • preflight_deckDry 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 p…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Check a deck before spending
  • start_jobStep 2: queue a job whose deck tarball has been uploaded.Reads text others writeNo findings

    Why it is in this group

    • The name "start_job" says "start": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Step 2: queue a job whose deck tarball has been uploaded. A GPU pod is launched; billing starts when it reports running.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Start an uploaded job
  • submit_jobOne call: create a hosted GPU job, upload the deck given INLINE as {relative_path: text}, and queue it.Reads text others writeNo findings

    Why it is in this group

    • The name "submit_job" says "submit": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Submit a deck (inline files) and start it
Only reads 3Show 3 read-only tools
  • job_logThe last <= 20 thermo/log lines the running pod reported (30 s heartbeat).Reads text others writeNo findings

    Why it is in this group

    • The name "job_log" says "log": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    The last <= 20 thermo/log lines the running pod reported (30 s heartbeat). Full log.lammps is in the results tarball.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Job log tail
  • job_statusState (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 ver…Reads text others writeNo findings

    Why it is in this group

    • The name "job_status" says "status": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    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`).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Job status
  • list_jobsJobs of this API key, newest first.Reads text others writeNo findings

    Why it is in this group

    • The name "list_jobs" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: List jobs

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write14
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:38 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
11
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://api.forcefieldsilicon.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://api.forcefieldsilicon.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 11 tools that change things (2 destructive, 9 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.forcefieldsilicon.com/mcp: tools/list returned 14 tools to an anonymous client, including delete_results (destructive), cancel_job (destructive), guide (write), campaign_request (write), account (write) and 6 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 changed.~2 changedView diff

Install

Pinned to version 0.7.1. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__mdengine__job_status",
      "mcp__mdengine__job_log",
      "mcp__mdengine__list_jobs"
    ],
    "ask": [
      "mcp__mdengine__guide",
      "mcp__mdengine__campaign_request",
      "mcp__mdengine__account",
      "mcp__mdengine__submit_job",
      "mcp__mdengine__create_job",
      "mcp__mdengine__start_job",
      "mcp__mdengine__job_results",
      "mcp__mdengine__capabilities",
      "mcp__mdengine__preflight_deck"
    ],
    "deny": [
      "mcp__mdengine__delete_results",
      "mcp__mdengine__cancel_job"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as mdengine. Review it before you use it.

Capability tags behind 14 rules
  • mcp__mdengine__guide untrusted-input
  • mcp__mdengine__campaign_request untrusted-input
  • mcp__mdengine__account untrusted-input
  • mcp__mdengine__submit_job untrusted-input
  • mcp__mdengine__create_job untrusted-input
  • mcp__mdengine__start_job untrusted-input
  • mcp__mdengine__job_status untrusted-input
  • mcp__mdengine__job_log untrusted-input
  • mcp__mdengine__job_results untrusted-input
  • mcp__mdengine__list_jobs untrusted-input
  • mcp__mdengine__delete_results untrusted-input
  • mcp__mdengine__capabilities untrusted-input
  • mcp__mdengine__preflight_deck untrusted-input
  • mcp__mdengine__cancel_job untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.forcefieldsilicon/mdengine/verify?hash=384f22298b0ec39e94b7b3a0b35d559d048d6183ca1a5d95c4f25104a5c0c010" | jq -e '.changed == false'

Pinned hash 384f22298b0e, from Nov 10, 2026, 16:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.forcefieldsilicon/mdengine/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.forcefieldsilicon/mdengine
[![Anlyon Radar](https://radar.anlyon.com/badge/com.forcefieldsilicon/mdengine.svg)](https://radar.anlyon.com/servers/com.forcefieldsilicon/mdengine)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:55 UTC.

MDEngine MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the MDEngine MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 11 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the MDEngine MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: delete_results and cancel_job.

Can the MDEngine MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the MDEngine MCP server have?

14 tools: 2 destructive, 9 write, 3 read. delete_results, cancel_job, guide, campaign_request, account, submit_job, create_job, start_job and 6 more.

Does the MDEngine MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the MDEngine MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the MDEngine MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.