Rent whole RTX PRO 6000 Blackwell GPUs in Montréal: quote, book, connect, stop, billing.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional. An API key from the console (Account, API keys) opens the account tools: bookings, deployments, billing and usage. Pricing, availability and quotes need no key. A sandbox key simulates everything and charges nothing.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
One yes or no per GPU model: is it free right now. A no does not block a request; the request waits for capacity.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http turbo https://exducer.ai/mcp
Headers
Authorization (optional, not in the config above): Optional. An API key from the console (Account, API keys) opens the account tools: bookings, deployments, billing and usage. Pricing, availability and quotes need no key. A sandbox key simulates everything and charges nothing.One yes or no per GPU model: is it free right now. A no does not block a request; the request waits for capacity.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}Send a GPU request. It is created as requested or queued and becomes running later (use wait_for_deployment); nothing is charged before it runs, then credit is drawn per minute. Quote first with quote_booking and get the user's yes on the total. Retry-safe: see idempotency_key.
| Argument | Type | Description |
|---|---|---|
| gpus* | integer | Number of GPUs: one of the server's allowed_gpu_counts. |
| hours* | integer | Duration in hours. A live booking has a minimum (the API answers duration_below_minimum under it). |
| image | string | A container image instead of a template. Only images the platform already runs are accepted. |
| notes | string | A note for the staff who place the request. |
| confirm* | boolean | Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely. |
| template | string | Template slug from list_templates. Left out: the default PyTorch image. |
| server_id* | string | Server id from list_servers. |
| auto_renew | boolean | Renew by itself at the end of the term while credit lasts. |
| renew_hours | integer | The renewal block in hours. |
| sandbox_speed | integer | Sandbox keys only: shorten every simulated wait this many times. |
| ssh_public_key | string | The text of the user's SSH public key (.pub), one key per line. Left out, the keys saved on the account are used. Required with a sandbox key. |
| idempotency_key | string | Optional. 8 to 128 characters. Reuse the same value when retrying the same request. Left out, one is derived from the request and the UTC date, so the identical request the same day returns the first answer; pass a new value to really do it a second time. |
| client_reference | string | Your own reference for this deployment; unique among the account's live deployments. |
| sandbox_scenario | string | Sandbox keys only: the lifecycle to simulate. |
{
"type": "object",
"required": [
"server_id",
"gpus",
"hours",
"confirm"
],
"properties": {
"gpus": {
"type": "integer",
"maximum": 4096,
"minimum": 1,
"description": "Number of GPUs: one of the server's allowed_gpu_counts."
},
"hours": {
"type": "integer",
"maximum": 720,
"minimum": 1,
"description": "Duration in hours. A live booking has a minimum (the API answers duration_below_minimum under it)."
},
"image": {
"type": "string",
"maxLength": 255,
"description": "A container image instead of a template. Only images the platform already runs are accepted."
},
"notes": {
"type": "string",
"maxLength": 1000,
"description": "A note for the staff who place the request."
},
"confirm": {
"type": "boolean",
"description": "Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely."
},
"template": {
"type": "string",
"maxLength": 120,
"description": "Template slug from list_templates. Left out: the default PyTorch image."
},
"server_id": {
"type": "string",
"description": "Server id from list_servers."
},
"auto_renew": {
"type": "boolean",
"description": "Renew by itself at the end of the term while credit lasts."
},
"renew_hours": {
"type": "integer",
"maximum": 720,
"minimum": 1,
"description": "The renewal block in hours."
},
"sandbox_speed": {
"type": "integer",
"maximum": 60,
"minimum": 1,
"description": "Sandbox keys only: shorten every simulated wait this many times."
},
"ssh_public_key": {
"type": "string",
"maxLength": 4096,
"description": "The text of the user's SSH public key (.pub), one key per line. Left out, the keys saved on the account are used. Required with a sandbox key."
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"minLength": 8,
"description": "Optional. 8 to 128 characters. Reuse the same value when retrying the same request. Left out, one is derived from the request and the UTC date, so the identical request the same day returns the first answer; pass a new value to really do it a second time."
},
"client_reference": {
"type": "string",
"maxLength": 128,
"description": "Your own reference for this deployment; unique among the account's live deployments."
},
"sandbox_scenario": {
"enum": [
"immediate",
"busy",
"marketplace_release",
"fail_start",
"host_unreachable",
"insufficient_credit",
"capacity_timeout",
"slow_start"
],
"type": "string",
"description": "Sandbox keys only: the lifecycle to simulate."
}
},
"additionalProperties": false
}Add hours to the term of a deployment that is requested, queued, provisioning or running. Same machine, same SSH details; billing stays per minute. Tell the user the extra cost (hours × gpu_count × rate) and get a yes first. Retry-safe: see idempotency_key.
| Argument | Type | Description |
|---|---|---|
| id* | string | The deployment id (rnt_… on a live key, snd_… in the sandbox). |
| hours* | integer | Hours to add. The new end may not be more than 720 hours away. |
| confirm* | boolean | Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely. |
| idempotency_key | string | Optional. 8 to 128 characters. Reuse the same value when retrying the same request. Left out, one is derived from the request and the UTC date, so the identical request the same day returns the first answer; pass a new value to really do it a second time. |
{
"type": "object",
"required": [
"id",
"hours",
"confirm"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,64}$",
"description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
},
"hours": {
"type": "integer",
"maximum": 720,
"minimum": 1,
"description": "Hours to add. The new end may not be more than 720 hours away."
},
"confirm": {
"type": "boolean",
"description": "Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely."
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"minLength": 8,
"description": "Optional. 8 to 128 characters. Reuse the same value when retrying the same request. Left out, one is derived from the request and the UTC date, so the identical request the same day returns the first answer; pass a new value to really do it a second time."
}
},
"additionalProperties": false
}The account behind the API key (email, company, type), whether the key is a sandbox key, and the prepaid balance in CAD (simulated under a sandbox key).
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The prepaid balance and the most recent credit ledger lines (top-ups and charges) in CAD.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many ledger lines, newest first. |
{
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 200,
"minimum": 1,
"description": "How many ledger lines, newest first."
}
},
"additionalProperties": false
}One deployment in full: state and reason, SSH host and port, the host key fingerprint to verify, rate per GPU-hour, cost so far, start and end time, endpoints.
| Argument | Type | Description |
|---|---|---|
| id* | string | The deployment id (rnt_… on a live key, snd_… in the sandbox). |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,64}$",
"description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
}
},
"additionalProperties": false
}The state changes of a deployment, oldest first, each with its reason, actor and time. Read this to learn why a deployment failed, ended or is waiting.
| Argument | Type | Description |
|---|---|---|
| id* | string | The deployment id (rnt_… on a live key, snd_… in the sandbox). |
| limit | integer | How many events. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,64}$",
"description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
},
"limit": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "How many events."
}
},
"additionalProperties": false
}List prices in CAD: GPU-hour per GPU model, object storage per GB-month, and the Models API. Use this instead of any remembered price.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The public status of each service (console, API, GPU region, object storage, Models API).
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}Object storage: GB stored, active keys, price per GB-month and the amount billed this month (not available to a sandbox key).
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}What the account was charged for GPU time, object storage and the Models API over a date range, in CAD before tax. Only deployments that ran appear.
| Argument | Type | Description |
|---|---|---|
| to | string | Last day, YYYY-MM-DD, included. Default: today. |
| from | string | First day, YYYY-MM-DD, America/Toronto. Default: the first of the month. |
| group | string | day: one row per day and type. type: one row per type for the range. |
| deployment_id | string | Only the GPU time of this deployment. |
{
"type": "object",
"required": [],
"properties": {
"to": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Last day, YYYY-MM-DD, included. Default: today."
},
"from": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "First day, YYYY-MM-DD, America/Toronto. Default: the first of the month."
},
"group": {
"enum": [
"day",
"type"
],
"type": "string",
"default": "day",
"description": "day: one row per day and type. type: one row per type for the range."
},
"deployment_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,64}$",
"description": "Only the GPU time of this deployment."
}
},
"additionalProperties": false
}Every deployment of the account with its state, GPU count, rate, cost so far and end time. States: requested, queued, provisioning, running, then stopped, ended, failed or cancelled.
| Argument | Type | Description |
|---|---|---|
| include_sandbox | boolean | On a live key, also list sandbox deployments. |
{
"type": "object",
"required": [],
"properties": {
"include_sandbox": {
"type": "boolean",
"description": "On a live key, also list sandbox deployments."
}
},
"additionalProperties": false
}The account's invoices (not available to a sandbox key).
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The servers a booking can name: id (the server_id of quote_booking and create_booking), GPU model, price per GPU-hour in CAD, allowed_gpu_counts, region, and whether it is free now.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The SSH public keys saved on the account: a booking with no ssh_public_key uses them (not available to a sandbox key). Adding or removing keys is done by the user in the console.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}The templates a booking can name: slug, name, the container image it runs, category. Without a template a deployment runs the default PyTorch image.
| Argument | Type | Description |
|---|---|---|
| q | string | Free-text filter. |
| category | string | Only this category slug. |
{
"type": "object",
"required": [],
"properties": {
"q": {
"type": "string",
"description": "Free-text filter."
},
"category": {
"type": "string",
"description": "Only this category slug."
}
},
"additionalProperties": false
}What a booking would cost in CAD: GPU cost, tax and total for the whole duration, and the hourly rates. Books nothing and charges nothing. Always quote and show the user the total before create_booking.
| Argument | Type | Description |
|---|---|---|
| gpus* | integer | Number of GPUs: one of the server's allowed_gpu_counts. |
| hours* | integer | Duration in hours. |
| server_id* | string | Server id from list_servers. |
{
"type": "object",
"required": [
"server_id",
"gpus",
"hours"
],
"properties": {
"gpus": {
"type": "integer",
"maximum": 4096,
"minimum": 1,
"description": "Number of GPUs: one of the server's allowed_gpu_counts."
},
"hours": {
"type": "integer",
"maximum": 720,
"minimum": 1,
"description": "Duration in hours."
},
"server_id": {
"type": "string",
"description": "Server id from list_servers."
}
},
"additionalProperties": false
}One documentation page as Markdown, by its slug (from search_docs). Read the page before answering a question about how the platform works.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The page slug, e.g. c-provisioning (from search_docs). |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9-]{1,64}$",
"description": "The page slug, e.g. c-provisioning (from search_docs)."
}
},
"additionalProperties": false
}Search the documentation by keyword. Returns the matching sections with a snippet and the slug to pass to read_doc.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many sections to return. |
| query* | string | What to look for, in a few words. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 6,
"maximum": 20,
"minimum": 1,
"description": "How many sections to return."
},
"query": {
"type": "string",
"description": "What to look for, in a few words."
}
},
"additionalProperties": false
}Turn automatic renewal of a deployment on or off. On, it keeps running and drawing credit past its end time until it is turned off or credit runs short, so get the user's yes first.
| Argument | Type | Description |
|---|---|---|
| id* | string | The deployment id (rnt_… on a live key, snd_… in the sandbox). |
| confirm* | boolean | Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely. |
| enabled* | boolean | true: renew at the end of each term while credit lasts. false: end as booked. |
| renew_hours | integer | The renewal block in hours (default 720). |
{
"type": "object",
"required": [
"id",
"enabled",
"confirm"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,64}$",
"description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
},
"confirm": {
"type": "boolean",
"description": "Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely."
},
"enabled": {
"type": "boolean",
"description": "true: renew at the end of each term while credit lasts. false: end as booked."
},
"renew_hours": {
"type": "integer",
"maximum": 720,
"minimum": 1,
"description": "The renewal block in hours (default 720)."
}
},
"additionalProperties": false
}Stop a deployment now: billing ends at this minute and its container and NVMe scratch disk are deleted and cannot be recovered. A request that has not started is withdrawn at no cost. Make sure results are copied off, tell the user the disk is deleted, and get a yes first.
| Argument | Type | Description |
|---|---|---|
| id* | string | The deployment id (rnt_… on a live key, snd_… in the sandbox). |
| confirm* | boolean | Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely. |
{
"type": "object",
"required": [
"id",
"confirm"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,64}$",
"description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
},
"confirm": {
"type": "boolean",
"description": "Must be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely."
}
},
"additionalProperties": false
}Poll a deployment until it reaches a state (default running) or a final state, for at most 50 seconds per call. Returns reached, the current state and whether it is final. While reached is false and final is false, call again; a live request can stay requested until staff place it, so after a few minutes tell the user and check back later instead of looping.
| Argument | Type | Description |
|---|---|---|
| id* | string | The deployment id (rnt_… on a live key, snd_… in the sandbox). |
| until | string | The state to wait for. |
| timeout_seconds | integer | How long to wait in this call. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,64}$",
"description": "The deployment id (rnt_… on a live key, snd_… in the sandbox)."
},
"until": {
"enum": [
"requested",
"queued",
"provisioning",
"running",
"stopped",
"ended",
"failed",
"cancelled"
],
"type": "string",
"default": "running",
"description": "The state to wait for."
},
"timeout_seconds": {
"type": "integer",
"default": 45,
"maximum": 50,
"minimum": 1,
"description": "How long to wait in this call."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 18, 2026.