# Akash Network MCP for AI Agents AI Agent Connect > Akash Network MCP lets you manage decentralized GPU and cloud resources via your AI agent. You can create deployments from SDL manifests, poll for provider bids, manage escrow balances, and configure auto top-ups. It gives you direct control over high-performance compute for AI training and inference without the overhead of centralized providers. ## Overview - **Category:** cloud-infrastructure - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_EuiIRYnmcVok7TPlrVtxL0krEFU1GLjnS5iObiJa/ai-agent-connect - **Tags:** gpu-computing, decentralized-cloud, sdl-manifest, akash-network, infrastructure-as-code ## Description Imagine you're trying to spin up a cluster of high-end GPUs for a massive training run. Usually, that means jumping between cloud consoles, hunting for available inventory, and manually configuring every single instance. This Connector changes that by letting your AI agent handle the heavy lifting on the Akash Network. You can describe the infrastructure you need, and the agent interacts with the decentralized cloud to find the best prices and secure the hardware. It handles the bidding process, manages the leases, and keeps an eye on your escrow balances to make sure your jobs don't get cut off mid-run. If you're already using Vinkius to manage your AI tools, adding this Connector makes it way easier to scale your decentralized compute. It's about moving from manual configuration to just telling your agent what you need to get done. ## Tools ### create_lease Accepts a provider bid and creates a lease for your compute resources. It locks in your hardware at a specific price. ### get_deployment_settings Retrieves the current auto top-up settings for a specific deployment. Use this to check your automation status. ### get_deployment Fetches full details and status for a specific deployment. It provides a complete overview of your active workload. ### get_provider Shows specific details for a provider on the Akash network. Use this to vet the hardware and reliability of a host. ### update_deployment_settings Modifies the configuration settings for an active deployment. Use this to make live changes to your running infrastructure. ### update_deployment Updates the details of an existing, active deployment. This allows for granular adjustments to your running workloads. ### create_deployment Creates a new deployment using a standard SDL manifest. This is the primary way to launch your infrastructure. ### list_bids Polls for provider bids for a specific deployment. This lets your agent find the best available price for your needs. ### list_deployments Lists all deployments currently running on your account. It gives you a high-level view of your entire fleet. ### list_providers Shows a list of all network-wide providers. This helps you see the breadth of available hardware on the network. ### close_deployment Ends an active deployment and releases the associated resources. This helps you free up hardware and stop costs. ### add_deposit Adds USD funds to a deployment escrow to extend your runtime. Use this to prevent your jobs from stopping early. ### enable_auto_top_up Turns on auto top-up settings to keep your services running. It automates your funding so you don't have to monitor it. ## Prompt Examples **Prompt:** ``` List all my active deployments on Akash. ``` **Response:** ``` I've retrieved your deployments. You have 2 active workloads: **AI-Training-Cluster** (DSEQ: 105542) and **Web-App-Node** (DSEQ: 105548). Would you like to check the escrow balance for either of them? ``` **Prompt:** ``` Add a $10 deposit to deployment 105542. ``` **Response:** ``` Processing deposit... I have successfully added **$10.00 USD** to the escrow for DSEQ 105542. The new balance is now **$14.50 USD**, extending your estimated runtime. ``` **Prompt:** ``` Close the deployment with DSEQ 105548. ``` **Response:** ``` Closing deployment... DSEQ 105548 has been successfully closed. Associated resources have been released and the remaining escrow balance will be returned to your account. ``` ## Capabilities ### Create GPU deployments from SDL manifests Spin up new decentralized compute resources using your standard infrastructure as code files. ### Poll for the best provider bids Let your agent find the most competitive pricing for your specific hardware requirements. ### Secure compute resources by creating leases Accept provider bids and lock in your hardware to ensure your workloads have a place to run. ### Add USD deposits to deployment escrows Keep your services running by adding funds to your active deployment balances via natural language. ### Configure auto top-up settings Ensure your decentralized infrastructure scales and stays online without manual intervention. ### Retrieve full details of active leases Get a clear picture of your current deployment statuses and hardware usage at any time. ## Use Cases ### Training a large language model An AI researcher needs 8x H100s. They ask the agent to find a provider and create a lease for a training job. ### Managing a dApp backend A developer wants to ensure their nodes stay up. They use the agent to enable auto top-up for their active deployments. ### Scaling inference A startup needs to scale GPU inference. They use the agent to create deployments from an SDL manifest as demand spikes. ### Auditing spend A DevOps lead wants to see what's running. They ask the agent to list all deployments and check the escrow balances. ## Benefits - Stop manual bidding by using list_bids and create_lease to automate how you secure GPU hardware. - Keep your training jobs running without interruption by using add_deposit to manage your escrow balance. - Standardize your infrastructure as code by using create_deployment with your existing SDL manifests. - Monitor your entire fleet in one place using list_deployments to see every active workload. - Scale your infrastructure automatically with enable_auto_top_up to ensure your resources never go offline. - Get instant visibility into provider availability using list_providers to find the best hardware for your needs. ## How It Works The bottom line is you get a natural language interface for managing decentralized GPU infrastructure. 1. Subscribe to the Akash Network MCP on Vinkius. 2. Enter your Akash API Key into your AI client settings. 3. Ask your agent to spin up a deployment or check your current balances. ## Frequently Asked Questions **What is the Akash Network MCP for?** It lets you manage decentralized GPU and cloud resources using your AI agent. You can spin up hardware, manage bids, and handle payments without leaving your workspace. **Can I use this to train AI models?** Yes, it's specifically designed to help you find and lease high-end GPUs for training and inference on the Akash Network. **How do I manage my budget?** You can use the Connector to check escrow balances and add USD deposits directly through your AI client to keep your services running. **Does this support SDL manifests?** Yes, you can create and manage deployments using standard Stack Definition Language manifests for infrastructure as code. **How do I keep my deployments running 24/7?** You can enable auto top-up settings so the system automatically handles your funding as your resources are consumed. **Can I see which providers are available?** The Connector allows your agent to list all network-wide providers so you can choose the best hardware for your specific needs. **How do I check for available provider bids after creating a deployment?** Use the `list_bids` tool with your deployment's DSEQ. It typically takes 30-60 seconds for providers to submit bids for your workload. **Can I update a running deployment with a new SDL manifest?** Yes! Use the `update_deployment` tool. Provide the existing DSEQ and your revised SDL string to apply changes to your active resources. **How do I prevent my deployment from closing due to insufficient funds?** You can use `add_deposit` to manually add USD to the escrow, or use `enable_auto_top_up` to configure automatic funding based on your deployment's needs.