Irys MCP for AI. Check permanent data storage costs and query web3 history.
Works with every AI agent you already use
…and any MCP-compatible client








How this MCP server connects to your AI agent
Irys MCP connects your AI agent to permanent data storage on Irys, the provenance layer for web3 assets. You can calculate exact data storage costs using specific tokens, query historical records with GraphQL filters, and manage wallet balances across multiple chains.
This tool gives you direct access to transaction history and node metadata.
What AI agents can do with Irys Automation
Get balance
Checks the current crypto asset balance for a specific wallet address.
Fund account
Submits a transaction receipt to add funds to the monitored account.
Get transaction
Fetches detailed metadata for any single, known transaction ID.
Calculates the exact cost for storing a specific amount of data using various crypto tokens.
Searches and filters through past transactions by specific tags or criteria using GraphQL.
Retrieves current crypto asset balances for an address, or submits a transaction to fund the account.
Pulls specific status details, tags, and information related to any given transaction ID.
Ask an AI about this
Waiting for input…
What AI agents can do with Irys: 8 Tools for Permanent Data Storage
These tools allow your agent to interact with the Irys provenance layer, enabling you to check prices, search history, and monitor crypto accounts.
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 Irys on VinkiusGet Balance
Checks the current crypto asset balance for a specific wallet address.
Fund Account
Submits a transaction receipt to add funds to the monitored account.
Get Transaction
Fetches detailed metadata for any single, known transaction ID.
Get Info
Retrieves real-time configuration data and supported features from the Irys node...
Get Price
Calculates the storage price for a given amount of data using specified tokens like...
Query Transactions
Searches and filters historical transaction metadata by specific tags across GraphQL.
Submit Transaction
Sends a signed data transaction to the provenance layer.
Withdraw Account
Initiates a request to move funds out of the monitored account.
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 Irys, 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
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
Built on the Model Context Protocol (MCP) for 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 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The current way requires switching between three different dashboards:, Solved with Vinkius AI Gateway
Today, figuring out if a project can afford permanent web storage means jumping through hoops. You check the gas tracker for current costs; then you navigate to a separate GraphQL explorer to see what tags exist; finally, you open your wallet dashboard just to confirm you have enough crypto left to pay for it all.
With this MCP, those three manual steps vanish. Your agent handles it all in one go. You simply ask the question, and the system gives you a single, actionable answer that combines pricing, availability, and data history.
Irys MCP: Direct access to provenance metadata
Before this tool, if you needed detailed proof of an event, you had to manually copy a transaction ID and then paste it into several different web pages just to gather all the associated tags, status updates, and creator details.
Now, giving your agent a single command triggers `get_transaction`, and you get every piece of metadata, clean and organized. It's that simple.
What your AI can actually do with this
Your AI client needs a way to see what happened on the permanent web without leaving your environment. This MCP handles that connection, allowing your agent to read data directly from Irys nodes. Instead of jumping between gas trackers, GraphQL explorers, and wallet dashboards, you can ask your agent questions like, 'How much will it cost to store 1GB using Solana?' or 'Show me all transactions tagged with App-Name: Vurb.' The system runs the complex queries for you.
When you subscribe to this MCP through Vinkius, your agent gets immediate access to the entire catalog of tools needed to monitor data permanence and storage economics. You can track node health via get_info, get current wallet balances using get_balance, and even manage funding or withdrawals with dedicated functions.
019ea5f2-f493-7317-a4ef-ace22f193cf3 Here's how it actually works
The bottom line is that your agent gets a direct pipeline into permanent web data, eliminating manual lookups across multiple developer dashboards.
Subscribe to this MCP and provide your Irys Node URL (Mainnet or Devnet).
Direct your AI agent to perform a task, such as finding the price for 1GB of storage.
The agent executes the necessary tool call, and you receive the real-time data back in plain text.
Who is this actually for?
Web3 developers who build applications needing verifiable data provenance. Data analysts tracking on-chain activity for research. DevOps engineers managing node health and funding status.
Needs to check upload prices or transaction statuses directly from their IDE while building a dApp.
Tracks historical on-chain activity by querying specific tags across the entire provenance layer for deep research.
Automates monitoring of Irys node balances, ensuring accounts are funded and operational status is confirmed.
What Changes When You Connect
Know your costs before you commit. Use get_price to calculate the exact, atomic-unit cost for storing any amount of data on tokens like Ethereum or Solana.
Track down specific historical activity instantly. Run complex searches using query_transactions with GraphQL filters to find records tied to unique tags.
Keep your node running smoothly. You can monitor current wallet funds via get_balance and initiate funding or withdrawals through dedicated tools.
Get deep details on any event. Use get_transaction to pull all the specific metadata, status, and tags associated with a single transaction ID.
Maintain operational visibility. The get_info tool provides real-time data about the Irys node's version and what features it supports.
See it in action
A new project needs to estimate deployment costs.
The developer asks their agent, 'What is the storage price for 10MB using Matic?' The agent uses get_price and returns a precise cost figure, allowing the dev to budget immediately without leaving their terminal.
Investigating suspicious on-chain behavior.
A data analyst asks the agent to 'Find all transactions tagged with 'Project X' that occurred last month.' The agent runs query_transactions and returns a list of IDs, enabling rapid investigation.
Automating node maintenance checks.
The DevOps engineer asks the agent to check the node status. The agent uses get_info and confirms that the current node version is active and reports all supported tokens, ensuring compliance.
Verifying a specific data upload record.
A user provides a transaction ID and asks for details. The agent calls get_transaction, which returns the full metadata, confirming the status and tags attached to that permanent record.
The honest tradeoffs
Assuming data is always visible.
Thinking you can just search for a general topic without knowing the specific tag used when the data was uploaded. The query fails or returns nothing useful.
Always use query_transactions and specify tags or filters, making sure your agent targets the correct metadata field to narrow down results.
Running out of node funds mid-process.
A transaction fails because the funding account balance was never checked or topped up before submission.
First, run get_balance to check assets. If necessary, use fund_account immediately before calling submit_transaction.
Mistaking a general query for a specific lookup.
Asking the agent for 'all transactions' when you actually only need details on one event.
If you have an ID, use get_transaction directly. If you need to search by tags, use query_transactions. Don't try to combine both methods.
When It Fits, When It Doesn't
Use this MCP if your workflow requires reading or writing data related to permanent web provenance: checking costs (get_price), tracking history (query_transactions), verifying node status (get_info), or managing funds. You need it when the source of truth is a distributed, immutable ledger.
Don't use this if you only need real-time communication (use a messaging MCP) or simple computation that doesn't require external web3 data. If your goal is just to read cached API results, another general REST tool might suffice. But when the permanence and verifiability of the stored data are critical, this Irys MCP is what you need.
Questions you might have
How do I use the Irys MCP to check storage pricing? +
You call the get_price tool. You must provide three pieces of information: the desired data size, the specific crypto token (like Solana), and the function will return the exact cost in atomic units.
Can I use query_transactions to find a record by date? +
Yes, query_transactions is designed for filtering. You can set up GraphQL filters within your prompt to target specific time ranges or tags associated with the data.
What is the difference between get_transaction and query_transactions in Irys MCP? +
Use query_transactions when you are searching a broad set of records by criteria (like 'all transactions tagged X'). Use get_transaction only when you already know the exact ID.
Do I need to use submit_transaction every time I make changes? +
No. You use submit_transaction when you actively want to push new signed data to the provenance layer. Other tools, like get_balance, are read-only.
How do I ensure my node account is funded before submitting data? +
Check balances first using get_balance. If funds are low, you can run fund_account to submit the necessary funding transaction receipt.
We've already built the connector for Irys. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 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.