How to Use the Filebase (Web3 Storage) MCP in Vercel AI SDK

Stream Filebase (Web3 Storage) data directly into your AI SDK frontends. Watch your UI update in real-time as your agent works.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Filebase (Web3 Storage) MCP to Vercel AI SDK

Create your Vinkius account to connect Filebase (Web3 Storage) to Vercel AI SDK 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 Filebase (Web3 Storage) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live IPFS content streaming

Pipe file contents straight from the network into your React components. Use `rpc_cat` to pull raw data into your stream without waiting for background jobs to finish. Your users see the output immediately. Because the MCP Server connects to your edge functions, the data flows as soon as the agent resolves the CID.

Automated pinning for your AI SDK

Ensure your content stays available by triggering `psa_add_pin` during your generation loop. This keeps your data persistent on the Filebase (Web3 Storage) layer without manual intervention. Handle the lifecycle of your uploads inside your stream. When the agent finishes a task, it tags the resulting CID for long-term storage automatically.

Manage IPNS names in real-time

Update your public pointers dynamically using `rpc_name_publish` and `platform_update_name`. Your application frontends can resolve these names to show the latest version of your data. It removes the need for database lookups or hardcoded links. The agent updates the record, and the UI reflects the change on the next render.

Setup guide

Set up Filebase (Web3 Storage) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Filebase (Web3 Storage) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Filebase (Web3 Storage) transactions",
});

console.log(text);
await mcpClient.close();

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 Filebase. 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 Filebase (Web3 Storage) 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 Filebase (Web3 Storage) MCP in Vercel AI SDK

Install the MCP client packages and point them to your server URL. You then pass the tool definitions directly into your generateText calls to give your agent access to your storage.

Yes, standard try-catch blocks wrap your tool calls. You can inspect the error response from the server and have the agent retry the operation or notify the user.

The server supports the streaming protocol natively. Results from tools like `rpc_cat` appear in your UI as they arrive from the network.

Your data stays within your controlled storage buckets. The server only performs the operations you explicitly authorize through your agent's tool calls.

You provide your credentials via environment variables during server startup. The server uses these to authenticate every request made by your agent.

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