EMT Compute is answering right now. Last checked 15 min ago. It exposes 22 tools.
GPU nodes and clusters, custom experiments, AI training and calculation reports for team workspaces.
Uptime history
4 days of history · worst day 99%
4 days agonow
100.0%
Uptime 24h
91 of 91 checks
22
Tools
read from the server
503 ms
Response time
average over 24h
open, no key
Access
streamable-http
What changed 23
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 5 November 2026. No other catalogue keeps this.
7 Nov
16 tools changed the parameters they ask for
emt_attach_cluster_experiment, emt_cancel_experiment, emt_catalog and 13 more
7 Nov
a tool changed version
6 Nov
2 tool descriptions were rewritten
emt_rent, emt_templates
6 Nov
a tool appeared
emt_environments
6 Nov
a tool changed the parameters it asks for
emt_rent
6 Nov
a tool changed version
5 Nov
a tool changed version
EMT Compute missed one check this week
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.
run in your terminal
claude mcp add emt-compute --transport http https://emtcompute.com/mcpSettings → Connectors → Add custom connector, then paste this address
https://emtcompute.com/mcp~/.codex/config.toml
[mcp_servers.emt-compute]
url = "https://emtcompute.com/mcp".cursor/mcp.json
{
"mcpServers": {
"emt-compute": {
"url": "https://emtcompute.com/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"emt-compute": {
"type": "http",
"url": "https://emtcompute.com/mcp"
}
}
}Available tools 22
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
emt
emt_attach_cluster_experiment
Attach work to an already rented dedicated 2–4-node cluster. Does NOT start SSH remotely: run emt_cluster.py locally with the returned job ID and your private key. Whole cluster stops on completion/cancel; billing continues during preparation.
emt_cancel_experiment
Cancel an owned experiment and request release of all its GPU nodes or attached cluster. Unfinished work can be lost. Recheck releasing until false.
emt_catalog
Current GPU offers. Prices in EUR micro-units per GPU/hour; unknown metrics remain null. Paginated to keep responses small.
emt_cluster_quote
Quote selected whole nodes on one fabric without renting.
emt_clusters
Current whole-node cluster offers; fabric declarations do not establish independent EMT qualification.
emt_environments
Verified environments (PyTorch, JAX, vLLM, TensorRT-LLM, ComfyUI, Unsloth) with their CUDA version and ports. Checked against the node before renting; they start an SSH server with the order's key.
emt_experiment_job
Inspect an owned experiment and its authenticated result, output and calculation-report download links. Files are not sent into the model context.
emt_experiment_jobs
Owned experiment jobs, including reports and release state. Requires read scope.
emt_experiment_presets
List scientific presets or inspect one preset's parameters, equations, methods and custom-input schema. Does not run a calculation.
emt_experiment_quote
Quote 1–4 nodes for an experiment; hours × hourly gives the GPU rental ceiling in micro-EUR. Reserve is only an initial hold, not total cost.
emt_monitor
Metrics and lifecycle for an owned order. Missing telemetry is unknown.
emt_orders
Owned GPU orders and lifecycle states. Requires read scope.
emt_quote
Create a fresh expiring GPU quote without renting or charging.
emt_rent
Start a PAID GPU rental with exactly one of environment (verified, from emt_environments: preferred) or template. Requires explicit spending authorization, fresh quote, rent scope, credit and accepted terms. Store payload and key before requesting.
emt_rent_cluster
Start a PAID whole-node cluster rental. Public SSH key only. Confirm cost and fabric limits with the user first.
emt_start_experiment
Start a PAID scientific preset, customer script or command. Parameter sets distribute across quoted nodes; this does not automatically parallelize a single solver. Auto-continuation may rent additional segments up to its budget. Review all costs before confirming.
emt_templates
Public GPU container templates for ordinary rentals. Prefer emt_environments: public templates can be refused when their CUDA is newer than the node's driver.
emt_terminate
Terminate every node in an owned rental. Local disks are deleted; retained volumes and backups remain billed. Inspect status until release is confirmed.
emt_training_events
Read up to 100 training events with metrics, runtime and observed dataset hashes when recorded. For full history start after=0 and latest=false, then repeat with the greatest returned seq until an empty page. latest=true returns the most recent window only. Visible devices are not proof of GPU utilization.
emt_training_job
Inspect an owned training job, its settings, lifecycle and recorded outcome.
emt_training_jobs
List owned AI training jobs. Requires read scope; does not start training or rent GPUs.
emt_training_recipe
Read the reproducible recipe for an owned training job, including model, dataset and training settings.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://emtcompute.com/mcp | streamable-http | answering | 734 ms | 15 min ago |
Alternatives to EMT Compute
same job, measured the same wayKanera
by kanera
Manage Kanera workspaces, boards, cards, checklists, comments, notes, automations, and reports.
Splera
by sohaibt
A/B testing for vibe coders: create, track, and ship experiments from your AI coding agent.
Testers.ai CARBON Test Harness Lite
by jarbon
Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
CLIO Node Hardware
by iowarp
Report CPU, memory, disk, network, GPU and process information for local or remote nodes.
TrackingTime
by trackingtime
TrackingTime MCP server for time, projects, tasks, users, customers, services, and reports.
JMeter Docs
by qainsights
Apache JMeter community documentation, conversion tools, linters, and calculators for AI agents.
Queue CallBack
by queuecallback
Reporting, callback operations, queue settings and Custom IVR flows for RingCentral call queues.
SuperBooks
by superbooks
Financial OS for small businesses: transactions, invoices, customers, time tracking and reports.
EMT Compute — questions
Answers built from our own checks of this server.
What can EMT Compute do?
It exposes 22 tools, read directly from the server on our last check. Among them: emt_attach_cluster_experiment, emt_cancel_experiment, emt_catalog, emt_cluster_quote, emt_clusters, emt_environments and 16 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 EMT Compute 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 503 ms. The bar chart above shows every period we have measured.
How do I connect EMT Compute?
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 EMT Compute need an API key?
No. EMT Compute completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 22 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is EMT Compute?
It answers our handshake in 503 ms on average, which is faster than 23% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.