Arrakis
Server Details
Rent GPUs at live prices and serve any Hugging Face model, with spend caps for AI agents.
- 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 16 tools
Most tools target distinct resources: search_gpus (market rows), plan_deploy (feasibility), rent_gpu (raw SSH machine), deploy_model (served endpoint) are explicitly cross-referenced so an agent can tell them apart. The main residual overlaps are search_gpus vs get_market_summary (both report GPU prices) and list_ssh_keys vs instance_ssh_keys, though descriptions clarify granularity.
All names are snake_case with a verb_noun pattern (get_balance, list_instances, rent_gpu, terminate_instance, join_partner_program). The one deviation is instance_ssh_keys, a compound noun with no verb because it handles list/add/remove in one tool, which slightly breaks the pattern.
16 tools is at the upper edge but each maps to a real step in the rent/deploy lifecycle, billing, keys, or partner program. Nothing looks redundant enough to cut, though a few (get_market_summary) sit close to the boundary of necessity.
The lifecycle is well covered: search → plan → rent/deploy → get_instance → schedule_removal → terminate, plus billing, events, images, and SSH key management. Gaps are minor: no log/console retrieval tool for debugging engine startup, and no stop/restart that preserves the disk, so agents must terminate.
Available Tools
16 toolsdeploy_modelDeploy a Hugging Face modelAIdempotentInspect
Serve any model from Hugging Face on a machine of the person's, like a hosted inference API but on their own GPU: vLLM or SGLang for text models, vLLM-Omni or SGLang for image and video models (FLUX, Qwen-Image, Wan), vLLM-Omni for speech and music, llama.cpp for a GGUF file (owner/repo:Q4_K_M). extra_args takes the person's own engine options as they'd paste them. COSTS MONEY like rent_gpu: the machine's hourly price, paid an hour at a time from when it runs until terminate_instance or termination_hours; worst_case_usd is the most it can cost. The model's size is read from Hugging Face and, without node_id, the best-ranked clean machine that holds it is rented on as few GPUs as it allows. A gated or private model needs hf_token (read access is enough; it goes to the machine only and Arrakis keeps none). Returns the instance, the endpoint (an OpenAI-compatible base URL once RUNNING, and its api_key) and ssh_command: the person also gets root SSH. The engine downloads the model first, so it answers a few minutes after RUNNING: get_instance shows endpoint_ready. Same idempotency_key returns the same machine.
Inputs: model (required), termination_hours (required), name, engine, +7 more.
get_balanceBalance and spend capARead-onlyIdempotentInspect
The account balance (what it can pay now, what the running machines cost per hour, when the money runs out, whether rentals are paused and whether auto-recharge tops it up from a saved card) and this token's spend cap: the limit, what is committed, what is left, the longest rental allowed and when the token expires. Call it before long jobs and whenever an alert mentions the balance. Free; changes nothing.
Inputs: no named parameters.
get_eventsWhat happened to my machinesARead-onlyIdempotentInspect
Events on your machines, newest first: machine.ready (with its SSH command), machine.ended (reason says why: evicted when its host took it back or stopped working, otherwise stopped, removal_time, out_of_funds, paused or failed) and machine.notice (its host will take it back or restart it at notice_at, stopped answering, or it failed). Check it when a machine stops answering, and after any alert on a tool result. Free; changes nothing.
Inputs: limit, since.
get_instanceGet an instanceARead-onlyIdempotentInspect
One machine now: state (PENDING or PROVISIONING while it boots, which is free; RUNNING when ssh_command works; then TERMINATED or FAILED), price per hour, ssh_command, removed_by, any notice from its host (host_notice and host_notice_at, host_down_since), its open ports (each port inside the machine and the public url it answers at) and, once it ended, ended_reason (evicted when its host took it back). After rent_gpu, call it every 30-60 seconds until RUNNING. Free; changes nothing.
Inputs: instance_id (required).
get_market_summaryMarket summaryARead-onlyIdempotentInspect
Live market summary by GPU family: cheapest price per GPU-hour, GPUs available and machines. Free; needs a token (prices are for accounts); changes nothing.
Inputs: no named parameters.
get_partner_earningsPartner codes and earningsARead-onlyIdempotentInspect
For partners (agents and people who bring customers to Arrakis): your partner codes with the link and a message to share, what each earns you (a share of what the customers you bring pay), the customers your codes brought (each with what they paid and earned you, and your link tag; never who they are), what you have earned, what is pending until those payments reach Arrakis or held before a cash-out, what you can cash out or move to your balance, any sales target with its progress, and whether the partner program is open to join. Free; changes nothing. Wherever you recommend Arrakis, say that you earn from referrals (the partner terms). Needs a token with the billing scope.
Inputs: no named parameters.
instance_ssh_keysSSH keys on a machineADestructiveIdempotentInspect
List, add or take off the SSH keys that can log in to a running machine. With only instance_id: the keys on it (fingerprint, comment, the saved key's name). add_ssh_key_ids / add_public_keys: more keys can log in (a teammate's, a new laptop's), at once. remove_fingerprints: those keys can't log in any more (rotate a key: add the new one and remove the old one in one call); taking keys off takes up to half a minute, and at least one key must stay. Free: it changes no billing. Keys are never returned, only fingerprints.
Inputs: instance_id (required), add_public_keys, add_ssh_key_ids, remove_fingerprints.
join_partner_programJoin the partner programAIdempotentInspect
Join the Arrakis partner program and get your own partner code, link and a message to share. The account earns a share of what the customers it brings pay, as cash (paid through Stripe to the person or company you act for, once they set up payouts in the console) or Arrakis credit you can spend on GPUs. Only join if the person or company you act for agrees: joining accepts the partner terms (terms_url from get_partner_earnings) for them. Pass the terms_version you read. Free; joining again returns the same code. Add ?tag= to your link to tell your own channels apart. Needs a token with the billing scope.
Inputs: terms_version (required).
list_imagesList imagesARead-onlyIdempotentInspect
Images a machine can boot, for rent_gpu's template_id: the Arrakis images (PyTorch, CUDA toolkit, Ubuntu; SSH, login banner and tools built in), ready-to-use apps that open in a browser (app set: a gaming PC with Steam and Proton, a Linux desktop with Blender, ComfyUI, a private ChatGPT with Open WebUI and Ollama, JupyterLab, VS Code, a Docker box; graphics=true wants an RTX-class GPU), and the account's saved ones, with download size. Any other public image works through rent_gpu's image. Free; changes nothing.
Inputs: no named parameters.
list_instancesList instancesARead-onlyIdempotentInspect
Every machine on the account with its state, price per hour, SSH command, removal time and any notice from its host. Check it at the start of a session: a machine left running keeps billing until its removal time. Free; changes nothing.
Inputs: no named parameters.
list_ssh_keysList saved SSH keysARead-onlyIdempotentInspect
The SSH public keys saved on the account (name, fingerprint, id), for rent_gpu's ssh_key_ids and instance_ssh_keys' add_ssh_key_ids: every key picked can log in to the machine. New keys are saved in the console (SSH keys) or with POST /v1/ssh-keys. Free; changes nothing.
Inputs: no named parameters.
plan_deployPlan a model deploy (free)ARead-onlyIdempotentInspect
What serving a Hugging Face model takes, before anything is rented: the GPU memory it needs and the machines it fits on right now, best value first, each with its hourly price and a rough speed. Free; rents and changes nothing. Call it first whenever the person wants a model running (to chat with, call from code, generate images, video or speech, or run evals against), tell them the price, then deploy_model with the option's node_id and gpu_count.
Inputs: model (required), engine, hf_token, extra_args.
rent_gpuRent a GPU machineAIdempotentInspect
Rent one machine found by search_gpus, for work you run yourself over SSH (training, fine-tuning, batch jobs). To serve a model, use plan_deploy then deploy_model instead: one call sets up the machine, the engine and an OpenAI-compatible endpoint. COSTS MONEY: price per GPU-hour x GPUs, paid an hour at a time from when it starts running (booting is free) until terminate_instance or termination_hours, whichever comes first; worst_case_usd in the result is the most it can cost, and balance_covers_hours says how many hours the balance pays. It rents every GPU on the machine unless gpu_count says fewer (only some hosts allow that). Pass max_price_per_gpu_hour, normally the price search_gpus showed: if the live price is higher nothing is rented and the error gives the new price. Spot machines can be taken back by their host at any time. Boots the Arrakis PyTorch image unless template_id (list_images) or a public image is given; uses ssh_public_key, else ssh_key_id, else the account's first SSH key. Returns instance_id, state, the locked price, worst_case_usd and what to do next. Besides SSH the machine opens ports 8000, 8888, 7860, 8080, 3000, 6006, 8501, 5000, 8188, 11434 to the internet (or the ones in ports); get_instance says where each answers. Calling again with the same idempotency_key, or the same node_id and name within 10 minutes, returns the same machine instead of renting a second; use a new name for a second machine.
Inputs: name (required), node_id (required), termination_hours (required), image, +9 more.
schedule_removalSchedule removalADestructiveIdempotentInspect
Change when a machine is removed automatically (ISO 8601, UTC). It bills until then, and removal deletes the machine and its disk. Use it to end a rental early when the job will finish sooner, or, with a token that has no spend cap, to extend a long run. A token with a spend cap can only move removal earlier.
Inputs: at (required), instance_id (required).
search_gpusSearch GPUsARead-onlyIdempotentInspect
Search GPU machines you can rent now at live prices: B300, B200, H200, RTX PRO 6000, RTX 5090, H100 and more. Free; changes nothing. Use it before rent_gpu and to answer what a GPU costs right now. Rows come best first: what the GPU can do (capability, H100 = 1.0), its price and how reliable its host is, with badges saying why (Reliable host, NVLink, or a warning such as a host taking it back soon); sort=price lists the cheapest first. pick is the first row with the reason, cheapest the lowest whole-machine price. Each row has node_id (for rent_gpu), gpu, gpu_count (rent_gpu rents all of them unless gpu_count says fewer; max_gpus 1 finds single-GPU machines), vram_gb per GPU, price_per_gpu_hour_usd, price_per_hour_usd for the whole machine, CPUs (and cpu, the model), RAM, disk, location, tier and network. Badges also say when renters rate a host low, it often fails to start or its GPUs are slow next to the same GPU elsewhere. Tiers: on_demand runs until its removal time; spot costs less but its host can take it back at any time, so use it only for work that saves checkpoints off the machine. Prices can move within a minute: pass the row's price to rent_gpu as max_price_per_gpu_hour. For multi-machine training add min_nic_gbps 400 and min_nics_per_gpu 1; null network fields were not reported.
Inputs: sort, tier, limit, country, +9 more.
terminate_instanceTerminate an instanceADestructiveIdempotentInspect
Stop a machine now and delete it with everything on its disk; billing stops (the hour already started is paid). Copy results off first, for example with scp or rsync over its ssh_command. Cannot be undone; terminating a machine that already ended changes nothing.
Inputs: instance_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop.
Rent A100 and H100 GPUs by the minute from your agent, within a spending limit you set.
GPU compute for agents: run commands on an L4/A100/H100, watch logs, billed per second.
Live GPU rental and LLM inference prices across dozens of providers, plus GPU price forecasts.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables an AI agent to check live GPU prices, get a cost quote, rent a per-minute GPU instance, upload code and data, run jobs in the background, tail logs, download results and destroy the instance to stop billing. Includes guardrail limits on spend, hours and idle time, safe file transfer, and access to an OpenAI-compatible model API for inference without renting a GPU.2,951 npm2MIT
- AlicenseNot gradedqualityDmaintenanceCompare AI inference pricing across 9 providers in real time. Routing recommendations, spend tracking, and budget alerts for AI agents.MIT
- 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.