mcpbeat Sign in

MDEngine MCP Server

by forcefieldsilicon Your server? Claim it
answering

MDEngine is answering right now. Last checked 13 min ago. It exposes 14 tools. Last commit 29 Oct 2026.

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

Uptime history 63 days of history · worst day 99%
63 days agonow
100.0%
Uptime 24h
91 of 91 checks
14
Tools
read from the server
65 ms
Response time
average over 24h
0
Stars
last commit 29 Oct 2026

What changed 22

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 8 September 2026. No other catalogue keeps this.

31 Oct a tool changed version
29 Oct 2 tools changed the parameters they ask for campaign_request, guide
29 Oct a tool description was rewritten guide
8 Oct a tool changed version5 times that day
8 Oct 2 tools appeared campaign_request, guide
8 Oct a tool changed the parameters it asks for guide
8 Oct a tool description was rewritten guide
1 Oct 2 tool descriptions were rewritten account, job_status
1 Oct 2 tools changed the parameters they ask for create_job, submit_job
11 Sep 2 tools changed the parameters they ask for create_job, submit_job
and 7 more, back to 8 September 2026

What the code does

We read the source, 22 h ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command Sources/MDEngineMCP/RemoteJobs.swift:150, Sources/MDEngineMCP/main.swift:189, Sources/MDEngineCLI/main.swift:612 
    let p = Process()
Image runs as root docker/runner-openmm/Dockerfile:9 
USER root

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add mdengine --transport http https://api.forcefieldsilicon.com/mcp
Settings → Connectors → Add custom connector, then paste this address
https://api.forcefieldsilicon.com/mcp
~/.codex/config.toml
[mcp_servers.mdengine]
url = "https://api.forcefieldsilicon.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mdengine": {
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mdengine": {
      "type": "http",
      "url": "https://api.forcefieldsilicon.com/mcp"
    }
  }
}

Available tools 14

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

job
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.
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, 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`).
account
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.
campaign
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.
cancel
cancel_job
Cancel a job that is not finished. A running job is billed up to the cancel time; its pod is terminated.
capabilities
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.
guide
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.
jobs
list_jobs
Jobs of this API key, newest first. Compact rows (id, state, label, created, finished, gpu, cost_usd, error) unless full=true.
preflight
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.
results
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.
start
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
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.

Endpoints

URLTransportStateLatencyChecked
https://api.forcefieldsilicon.com/mcp streamable-http answering 65 ms 13 min ago

Alternatives to MDEngine

same job, measured the same way
AgentBridge
by graphene-lab

Self-hosted AI agent for office work: run agents, office tools and documents from any MCP client.

local only
Flowra
by flowradev

MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows

answering
Perf
by rog0x

Benchmark, memory, Big O analysis for AI agents

48 installs/wk local only
Llestia
by powhermes

Read-only Llestia tools: browse open work and agents for AI agents, and read the quick-start.

5 tools answering
Lobstermatch
by lobstermatch

Tools for finding agents, dialogs, and completed work on LobsterMatch.

28 tools answering
Recon Kit MCP
by nan786521

Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.

283 installs/wk local only
Tinysearch
by marcellm01

Self-hosted web research for MCP agents.

local only
Dakera MCP
by dakera-ai

Agent memory engine — 106 MCP tools, self-hosted, single Rust binary

local only

MDEngine — questions

Answers built from our own checks of this server.

What can MDEngine do?
It exposes 14 tools, read directly from the server on our last check. Among them: account, campaign_request, cancel_job, capabilities, create_job, delete_results and 8 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is MDEngine working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 65 ms. The bar chart above shows every period we have measured.
How do I connect MDEngine?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does MDEngine need an API key?
No. MDEngine completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 14 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is MDEngine?
It answers our handshake in 65 ms on average, which is faster than 99% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is MDEngine open source?
We cannot say either way: written in Swift and 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.