Allnodes MCP for AI. Manage entire Web3 infra from your agent.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
Allnodes MCP manages your entire Web3 infrastructure stack directly through any AI agent. Get real-time data on staking delegations, monitor active validators, provision bare metal servers, and manage node operations—all without leaving your IDE or terminal.
It's the full command center for crypto infra.
What your AI can do
Add ssh key
Adds a new SSH public key, granting secure access credentials to your hosted infrastructure.
Get delegation
Retrieves the detailed status and metrics for one specific staking delegation.
Get delegations
Fetches a complete list of all current staking delegations you manage.
Retrieve lists of all full nodes, inspect specific validator details, or restart an existing node with one command.
Query available bare-metal servers and provision new hosting environments using instant server profiles or upgrades.
Perform critical staking actions—staking, unstaking, claiming, or withdrawing funds for various supported currencies.
Inspect validator health records, manage SSH public keys, and handle the registration lifecycle of your nodes.
Initiate hosting for a new full node or deploy an entire validator/masternode stack to begin operations.
Ask an AI about this
Waiting for input…
Allnodes (Staking and Web3 Hosting API) - 20 Tools
These tools let you programmatically manage every aspect of your crypto infrastructure, from deploying bare metal servers to executing complex staking transactions.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Allnodes (Staking and Web3 Hosting API) on VinkiusAdd Ssh Key
Adds a new SSH public key, granting secure access credentials to your hosted infrastructure.
Get Delegation
Retrieves the detailed status and metrics for one specific staking delegation.
Get Delegations
Fetches a complete list of all current staking delegations you manage.
Get Fullnode
Retrieves detailed metadata for one specific, active full node.
Get Fullnodes
Lists all currently managed full nodes and their basic status information.
Get Instant Server Profiles
Gets a list of all available software installation profiles for instant server deployment.
Get Instant Server Upgrades
Lists potential version upgrades or patches available for your instant servers.
Get Instant Servers
Retrieves a list of all currently deployed, instantly provisioned servers.
Get Servers
Lists all available bare-metal server hardware for immediate provisioning.
Get Ssh Keys
Retrieves a list of all SSH public keys currently registered to your account.
Get Validator
Fetches the current status and details for one specific validator instance.
Get Validators
Lists all managed validators, providing a summary of their health and status.
Host Instant Server
Provisions and deploys an instant server environment based on selected profiles or upgrades.
Host Node
Deploys a new validator, masternode, or full node instance to start running.
Prepare Deterministic
Prepares the necessary registration data for deterministic node setup and operation.
Remove Ssh Key
Removes a specific SSH public key, revoking access to your hosted infrastructure.
Remove Validator
Decommissions and removes an active validator from the network.
Restart Fullnode
Initiates a restart sequence for any listed full node, ensuring service uptime.
Staking Action
Executes critical staking operations like stake, unstake, withdraw, or claim for supported currencies.
Submit Deterministic
Finalizes and submits the prepared deterministic registration to the network.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Allnodes (Staking and Web3 Hosting API), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Allnodes. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 20 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Checking Node Status Used to Mean Switching Consoles
Today's process is tedious: You check the staking dashboard for reward data, then open a second tab to see if the full node is up, and finally switch over again to an infrastructure portal just to list available hardware. You end up copying dozens of IDs and pasting them into various CLI tools.
With this MCP, you ask your agent one question: 'Give me the status of all my compute resources.' It pulls data from every source—validators, full nodes, bare metal servers—and gives it back in a single, structured response. You get immediate clarity.
Handling Staking Actions with `staking_action`
Before this MCP, executing a stake or unstake required navigating complex UI flows and often meant dealing with manual confirmation codes. It was slow, brittle, and prone to human error.
Now, you just tell your agent: 'Unstake 10 ETH.' The `staking_action` tool handles the API calls, validates the currency, and executes the withdrawal request—all without leaving your conversation window. It's done.
What your AI can actually do with this
Managing blockchain nodes used to mean jumping between a dozen different dashboards: one for staking status, another for server provisioning, and a third just for SSH key management. Now, you can keep everything in your agent conversation. This MCP lets your AI client interact with non-custodial services for staking, node hosting, and validator management.
Whether you need to check all available compute resources or perform a complex financial operation like claiming rewards, the necessary commands are available through one single connection point. You just tell your agent what needs doing—like provisioning an instant server profile or restarting a full node—and it handles the sequence of calls.
This level of orchestration is why Vinkius hosts this MCP; it lets you treat complex infrastructure management like sending a simple chat message.
019e5cf9-affb-70ce-b8b3-ae5c47295749 Here's how it actually works
The bottom line is that you get to manage complex crypto infrastructure by talking to your AI client, instead of running dozens of API commands manually.
Subscribe to this MCP on Vinkius and enter your Allnodes API Token.
Your AI agent authenticates the connection, making all underlying infrastructure calls available.
You ask your agent for a specific action (e.g., 'List all my bare-metal servers'), and it returns structured data directly into your chat.
Who is this actually for?
This tool saves the DevOps engineer who spends hours clicking through multiple dashboards just to check node health. It's for the Crypto Infra Architect who needs immediate visibility into validator status or the Developer who can't leave their IDE while deploying a new test node.
Automates server provisioning, manages SSH keys, and deploys/restarts full nodes as part of a CI/CD pipeline run from the agent.
Maintains visibility across all active validators, monitors staking delegations, and orchestrates node deployments for new protocols.
Needs to retrieve specific node metadata or check available bare-metal server profiles before writing deployment code.
What Changes When You Connect
You stop having to switch between multiple dashboards. Your agent handles listing all full nodes (get_fullnodes) and checking validator status in one chat session.
Need a new node? Instead of going through the console, you can ask your agent to deploy it using host_node or provision an instant server via host_instant_server. It's hands-free deployment.
Staking is simplified. You don't need to look up staking APIs; just tell your agent to run a staking action (staking_action) and specify the currency.
Security management becomes trivial. Use add_ssh_key or remove_ssh_key directly in conversation, keeping your access logs clean without needing to SSH into a dashboard first.
When scaling up, you can query all available bare-metal hardware (get_servers) and immediately get the status of current validators using get_validators.
See it in action
Validator Health Check
The infra engineer needs to confirm if a specific validator is running correctly. They ask their agent for get_validator(ID), which immediately returns the status, uptime, and current rewards without manual API calls or dashboard navigation.
New Node Deployment
A developer needs to deploy a new ETH masternode. They ask their agent to host_node for an Ethereum validator, which handles the deployment sequence and provides necessary metadata before they even write the next line of code.
Auditing Access Keys
The security officer needs to know who has access. They simply ask their agent to get_ssh_keys, getting a complete list of all registered public keys in one conversational query.
Clearing Staking Funds
A user needs to withdraw staked SOL. Instead of navigating the staking portal, they ask their agent to perform the staking_action for 'unstake' and specify SOL, executing the transaction directly.
The honest tradeoffs
Checking Status in Chunks
Manually running get_fullnode(ID1) then forgetting to run get_fullnode(ID2) because the list is too long.
Always start by listing all assets. Use the group function, like requesting get_fullnodes, which gives you a complete roster of everything before checking individual nodes.
Mixing up Resource Types
Trying to run a staking action on a bare metal server ID instead of using the dedicated hosting API.
Keep resource types separate. Use get_servers for hardware listing, and reserve tools like staking_action strictly for financial operations.
Manually Updating Keys
Having to log into the web dashboard just to upload a new SSH key because your agent can't find it.
Use the explicit add_ssh_key tool. It handles adding and managing keys securely right from the chat interface.
When It Fits, When It Doesn't
You should use this MCP if your workflow requires coordinating actions across multiple, disparate systems—specifically staking protocols, compute hosting, and node management. If you need to check a validator's status and provision a new server and update an SSH key, this is the right toolset. Don't use it if you only need one simple thing, like reading a single list of servers; in that case, dedicated read-only APIs might be cleaner. Use this for complex state transitions and multi-step automation.
Questions you might have
How do I list all my servers using get_servers? +
You ask your agent to run get_servers. This tool returns a comprehensive list of every bare-metal server currently available for provisioning.
What is the difference between get_fullnodes and get_fullnode? +
Use get_fullnodes when you need a summary list of all managed nodes. Use get_fullnode when you already know the ID and only want detailed metadata for one specific node.
Can I use add_ssh_key to access my server? +
The add_ssh_key tool handles adding keys. After running it, your agent uses that key to secure your hosted infrastructure, giving you programmatic control over access.
How do I restart a node? Should I use restart_fullnode? +
Yes, restart_fullnode is the correct tool. You pass it the ID of the full node, and it executes the necessary maintenance action to bring the service back up.
If I want to check all my current staking positions, should I use get_delegations? +
Yes, get_delegations lists every stake you currently hold across different networks. The output shows the specific currency, the amount staked, and the recipient address for each delegation.
What is the necessary workflow if I decide to remove a validator using remove_validator? +
You must provide the exact Validator ID you intend to decommission. The system then verifies ownership and initiates the removal process, which takes effect immediately after confirmation.
Before hosting a new server, how do I see what installation templates are available using get_instant_server_profiles? +
This function pulls all predefined OS images and setup options offered by the platform. You can compare different distributions (like Ubuntu or CentOS) before choosing one to provision your machine with host_instant_server.
If I need to audit my access, how do I view or remove an SSH key using get_ssh_keys and remove_ssh_key? +
First, run get_ssh_keys to list all registered public keys with their IDs. Once you've identified the key you want gone, use remove_ssh_key with that ID to revoke access.
Can I list my active validators across all networks? +
Yes! Use the get_validators tool to retrieve a comprehensive list of all validators associated with your account, including their IDs and current status.
How do I add a new SSH key for my hosted servers? +
Simply use the add_ssh_key action. You'll need to provide an alias for the key and the public key string itself to register it in your Allnodes profile.
Is it possible to restart a full node through the AI? +
Yes. By using the restart_full_node tool with the specific Node ID, the agent can trigger a remote restart of your infrastructure.
We've already built the connector for Allnodes. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 20 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.