How to Use the Arweave MCP in Pydantic AI

Q: How do I register the Arweave MCP Server in Pydantic AI?

Use the unified MCPToolset class configured with your Vinkius HTTP endpoint. Pass the toolset instance directly into your Agent's toolsets list to expose permaweb tools like getnetworkinfo and submittransaction.

Q: What happens if an Arweave API response changes in Pydantic AI?

Pydantic AI will raise a validation error at runtime. If gettransaction returns a payload that doesn't match the expected type schema, the framework stops execution, ensuring no corrupted data enters your agent's state.

Q: Can I validate Arweave wallet balances using Pydantic AI?

Yes, when your agent calls getwalletbalance, the framework guarantees the returned Winston balance is validated as a clean integer. This prevents float precision issues when checking your transaction budget.

Q: How do I retrieve the last transaction sent by a wallet?

The agent can call getwalletlasttx with the target wallet address. This returns the transaction ID, which you can then pass to gettransactionstatus to check its confirmation state.

Build type-safe Python agents with Pydantic AI to validate Arweave permaweb data and transaction schemas at runtime with zero silent errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arweave MCP to Pydantic AI

Create your Vinkius account to connect Arweave to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Arweave with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe permaweb querying with Pydantic AI

The Arweave MCP Server integrates with your Pydantic AI agent to guarantee that every transaction or block response matches your strict Python models. When your agent calls `get_transaction` or `get_block_by_hash`, the framework validates the returned permaweb JSON structure before your agent logic ever touches it. This prevents runtime crashes caused by unexpected API variations or malformed block data. If a gateway returns an unexpected schema, your system fails loudly and immediately, preventing corrupted data from propagating through your pipeline.

Validate Arweave storage costs via this MCP Server

This MCP Server lets your type-safe agents monitor wallet health without risking type coercion errors. Your agent can call `get_wallet_balance` to get the exact Winston balance, which Pydantic AI validates against a strict integer schema. The agent can also query `get_storage_price` to calculate the exact cost of an upload. Because these values are strictly typed, your agent can safely perform mathematical checks before executing a write operation.

Structured tag searches via GraphQL

The Arweave MCP Server allows you to execute structured queries and parse them into clean Python objects. Your agent uses `query_graphql` to find transactions by tags, and the framework parses the nested GraphQL response into a clean, flat data model. This makes it easy to build reliable indexing agents. You write the Pydantic model for the expected tags, and the agent automatically rejects any transaction metadata that doesn't match your schema.

Setup guide

Set up Arweave MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "arweave-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Arweave tools.",
)

result = await agent.run("List recent Arweave transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Arweave. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Arweave now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Arweave MCP in Pydantic AI

Use the unified `MCPToolset` class configured with your Vinkius HTTP endpoint. Pass the toolset instance directly into your Agent's `toolsets` list to expose permaweb tools like `get_network_info` and `submit_transaction`.

Pydantic AI will raise a validation error at runtime. If `get_transaction` returns a payload that doesn't match the expected type schema, the framework stops execution, ensuring no corrupted data enters your agent's state.

Yes, when your agent calls `get_wallet_balance`, the framework guarantees the returned Winston balance is validated as a clean integer. This prevents float precision issues when checking your transaction budget.

The agent can call `get_wallet_last_tx` with the target wallet address. This returns the transaction ID, which you can then pass to `get_transaction_status` to check its confirmation state.

We run all tool executions inside isolated, short-lived V8 sandboxes. Your wallet addresses and transaction IDs are processed entirely in-memory and discarded instantly upon completion, keeping your queries secure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript