Exact date and time math for AI agents: business days with holidays in 207 countries, time zones, DST, SLAs, cron, RRULE and market calendars. 25 free calls a day.
Nothing to run from here
EMT Compute is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
21
tools declared
remote
at its publisher
—
calls last 7d
What it does
GPU nodes and clusters, custom experiments, AI training and calculation reports for team workspaces.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http emt-compute-mcp https://emtcompute.com/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'
# 2 — ask your agent for something these tools do
# emt_catalog, emt_clusters, emt_templates and 18 more
It needs AUTHORIZATION (Bearer API key created in the intended EMT workspace, with only the required scopes): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
EMT Compute costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
EMAll 1 server
emtcompute1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer API key created in the intended EMT workspace, with only the required scopes) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).
claude mcp add --scope user --transport http emt-compute-mcp https://emtcompute.com/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer API key created in the intended EMT workspace, with only the required scopes. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
21 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Current GPU offers. Prices in EUR micro-units per GPU/hour; unknown metrics remain null. Paginated to keep responses small.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | no | — |
| offset | integer | no | — |
| limit | integer | no | — |
Current whole-node cluster offers; fabric declarations do not establish independent EMT qualification.
No parameter schema on file.
Public GPU container templates for ordinary rentals.
No parameter schema on file.
List scientific presets or inspect one preset's parameters, equations, methods and custom-input schema. Does not run a calculation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | — |
Owned GPU orders and lifecycle states. Requires read scope.
No parameter schema on file.
Owned experiment jobs, including reports and release state. Requires read scope.
No parameter schema on file.
Inspect an owned experiment and its authenticated result, output and calculation-report download links. Files are not sent into the model context.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job | string | yes | — |
List owned AI training jobs. Requires read scope; does not start training or rent GPUs.
No parameter schema on file.
Inspect an owned training job, its settings, lifecycle and recorded outcome.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job | string | yes | — |
Read the reproducible recipe for an owned training job, including model, dataset and training settings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job | string | yes | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job | string | yes | — |
| after | integer | no | — |
| latest | boolean | no | — |
Metrics and lifecycle for an owned order. Missing telemetry is unknown.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order | string | yes | — |
Create a fresh expiring GPU quote without renting or charging.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | string | yes | — |
| count | integer | yes | — |
| hours | integer | yes | — |
Quote selected whole nodes on one fabric without renting.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cluster | string | yes | — |
| nodes | array | yes | — |
| hours | integer | yes | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| count | integer | no | — |
| nodes | integer | no | — |
| minVram | integer | no | — |
| model | string | no | — |
| fp64 | boolean | no | — |
| maxMinutes | integer | no | — |
| node | string | no | — |
| environment | string | no | — |
Start a PAID GPU rental. Requires explicit spending authorization, fresh quote, rent scope, credit and accepted terms. Store payload and key before requesting.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quote | string | yes | — |
| name | string | yes | — |
| template | string | yes | — |
| ssh | string | no | — |
| jupyter | boolean | no | — |
| volume | string | no | — |
| backups | boolean | no | — |
| ports | integer | no | — |
| confirm_paid_rental | boolean | yes | — |
| idempotency_key | string | yes | — |
Start a PAID whole-node cluster rental. Public SSH key only. Confirm cost and fabric limits with the user first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quote | string | yes | — |
| name | string | yes | — |
| ssh | string | yes | — |
| acknowledgeSlowNetwork | boolean | no | — |
| confirm_paid_rental | boolean | yes | — |
| idempotency_key | string | yes | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quotes | array | yes | — |
| name | string | yes | — |
| experiment | yes | — | |
| level | string | no | — |
| runs | array | yes | — |
| files | array | no | — |
| seed | integer | no | — |
| config | object | no | — |
| resume | object | no | — |
| auto | object | no | — |
| ssh | string | no | — |
| confirm_paid_rental | boolean | yes | — |
| idempotency_key | string | yes | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| experiment | yes | — | |
| level | string | no | — |
| runs | array | yes | — |
| files | array | no | — |
| seed | integer | no | — |
| config | object | no | — |
| ssh | string | no | — |
| clusterOrder | string | yes | — |
| maxMinutes | integer | no | — |
| releaseCluster | boolean | yes | — |
| idempotency_key | string | yes | — |
Cancel an owned experiment and request release of all its GPU nodes or attached cluster. Unfinished work can be lost. Recheck releasing until false.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job | string | yes | — |
| confirm_stop | boolean | yes | — |
Terminate every node in an owned rental. Local disks are deleted; retained volumes and backups remain billed. Inspect status until release is confirmed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order | string | yes | — |
| confirm_local_data_loss | boolean | yes | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install EMT Compute or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.2.1 · scanned 8 Nov 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest9d4b2ce0b7fed36167d0ac8c8d3303bc1e016e3780c392d1ac2b08f15dea0ee5
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| emt_catalog | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_clusters | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_templates | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_experiment_presets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_orders | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_experiment_jobs | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_experiment_job | untrusted-input | untrusted-input: keyword "download", declares openWorldHint: true (interacts with entities outside the server) |
| emt_training_jobs | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_training_job | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_training_recipe | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_training_events | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_monitor | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| emt_quote | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| emt_cluster_quote | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| emt_experiment_quote | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| emt_rent | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| emt_rent_cluster | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| emt_start_experiment | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| emt_attach_cluster_experiment | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| emt_cancel_experiment | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| emt_terminate | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest9d4b2ce0b7fed361
Scanned2026-11-08
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.2.1.
1.2.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish EMT Compute can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.