ExducerAI GPU cloud
Server Details
Rent whole RTX PRO 6000 Blackwell GPUs in Montréal: quote, book, connect, stop, billing.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 22 tools
Most tools target a clearly distinct resource+action (deployments, billing, docs, servers, SSH keys, templates). A few pairs overlap mildly — check_availability duplicates the per-server free-now flag in list_servers, and get_usage / get_storage_usage / get_billing all report cost data — but the descriptions disambiguate them effectively (account range totals vs storage-only vs balance+ledger).
Every tool follows a strict snake_case verb_noun pattern (get_*, list_*, create_booking, quote_booking, stop_deployment, extend_deployment, wait_for_deployment, read_doc, search_docs). Verb choice is semantically consistent: get_/list_ for reads, create_/set_/stop_/extend_ for mutations.
22 tools is above the ideal band but each maps to a distinct operation across four sub-domains (deployments, billing/storage, catalog/servers, documentation). Nothing appears redundant or filler; the surface is broad because the underlying cloud API is broad, not because of padding.
The deployment lifecycle is well covered (quote, create, wait, inspect, events, extend, auto-renew, stop) and billing, pricing, storage and docs are all present. Gaps are minor but real: no way to top up prepaid credit, no deployment log streaming (only state events), and SSH key and template management are read-only by design (console-only), which is documented rather than dead-ending an agent.
Available Tools
22 toolscheck_availabilityGPU availability nowARead-onlyIdempotentInspect
One yes or no per GPU model: is it free right now. A no does not block a request; the request waits for capacity.
Inputs: no named parameters.
create_bookingBook GPUsAIdempotentInspect
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.
Inputs: gpus (required), hours (required), confirm (required), server_id (required), +10 more.
extend_deploymentRun a deployment longerAIdempotentInspect
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.
Inputs: id (required), hours (required), confirm (required), idempotency_key.
get_accountAccount and balanceARead-onlyIdempotentInspect
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).
Inputs: no named parameters.
get_billingBalance and ledgerBRead-onlyIdempotentInspect
The prepaid balance and the most recent credit ledger lines (top-ups and charges) in CAD.
Inputs: limit.
get_deploymentOne deploymentARead-onlyIdempotentInspect
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.
Inputs: id (required).
get_deployment_eventsDeployment eventsARead-onlyIdempotentInspect
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.
Inputs: id (required), limit.
get_pricingList pricesARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
get_service_statusService statusARead-onlyIdempotentInspect
The public status of each service (console, API, GPU region, object storage, Models API).
Inputs: no named parameters.
get_storage_usageObject storage usageARead-onlyIdempotentInspect
Object storage: GB stored, active keys, price per GB-month and the amount billed this month (not available to a sandbox key).
Inputs: no named parameters.
get_usageUsage reportARead-onlyIdempotentInspect
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.
Inputs: to, from, group, deployment_id.
list_deploymentsDeploymentsARead-onlyIdempotentInspect
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.
Inputs: include_sandbox.
list_invoicesInvoicesBRead-onlyIdempotentInspect
The account's invoices (not available to a sandbox key).
Inputs: no named parameters.
list_serversBookable serversARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
list_ssh_keysSaved SSH keysARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
list_templatesTemplatesARead-onlyIdempotentInspect
The templates a booking can name: slug, name, the container image it runs, category. Without a template a deployment runs the default PyTorch image.
Inputs: q, category.
quote_bookingQuote a bookingARead-onlyIdempotentInspect
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.
Inputs: gpus (required), hours (required), server_id (required).
read_docRead a documentation pageARead-onlyIdempotentInspect
One documentation page as Markdown, by its slug (from search_docs). Read the page before answering a question about how the platform works.
Inputs: slug (required).
search_docsSearch the documentationARead-onlyIdempotentInspect
Search the documentation by keyword. Returns the matching sections with a snippet and the slug to pass to read_doc.
Inputs: query (required), limit.
set_auto_renewAutomatic renewalAIdempotentInspect
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.
Inputs: id (required), confirm (required), enabled (required), renew_hours.
stop_deploymentStop a deploymentADestructiveIdempotentInspect
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.
Inputs: id (required), confirm (required).
wait_for_deploymentWait for a deploymentARead-onlyIdempotentInspect
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.
Inputs: id (required), until, timeout_seconds.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Rent H100, RTX PRO 6000, A100, L40 and RTX A6000 GPUs by the hour in Montréal, Canada, in CAD.
Create and manage VMs, managed databases, firewalls and load balancers in Montréal, Canada.
Cloud GPU prices with live stock from 22 providers. Find where to rent an H100 or B300 now.
Live public cloud GPU rental prices (H100, A100, L40S and more) across 20+ providers.
Related MCP Servers
- AlicenseBqualityBmaintenanceZero-quota GPU orchestration MCP server — lets AI agents discover, provision, and manage GPU compute across multi-datacenter partner nodes (H100/H200/B200) through a single control plane.489 npmMIT
- FlicenseNot gradedqualityDmaintenanceProvision private AI model endpoints (Llama 3.1, Qwen 2.5, Mistral) on dedicated GPUs, billed per minute. OAuth 2.1 + DCR.-
- AlicenseNot gradedqualityCmaintenanceAutonomous Cloud GPU Spot Bursts (rent_gpu_burst_arbitrage): Scans wholesale spot orderbooks (RTX 3090, RTX 4090, A100, H100) and provisions on-demand 3-minute compute bursts ($0.0500 USDC) with an automated 180-second idle deadman destruction switch and warm-pool multi-agent reuse.MIT
- FlicenseNot gradedqualityCmaintenanceMCP server for renting real GPUs from the terminal. Enables browsing, renting, chatting, managing, and pooling GPU instances with per-second billing, designed for AI agents.1-
Glama MCP Gateway
Add one secure layer between your agents and this server.