How to Use the Farcaster (Decentralized Social Protocol) MCP in Vercel AI SDK

Q: How do I stream Farcaster (Decentralized Social Protocol) tools using Vercel AI SDK?

Install @ai-sdk/mcp and call createMCPClient with your HTTP endpoint. Pass the tools directly to streamText to let your agent call Farcaster tools like listallchannels on demand.

Q: Can I moderate channels in real-time with Farcaster (Decentralized Social Protocol) and Vercel AI SDK?

Yes. Your agent can call moderatecast to hide spam and immediately stream the updated action log back to your frontend. This keeps your interface in sync with the protocol state.

Q: How does this MCP Server handle Farcaster (Decentralized Social Protocol) identity resolution with Vercel AI SDK?

The agent calls tools like getcurrentfnamebyfid and listaccountverifications during the generation loop. The SDK streams the resolved handle and verified wallets directly to your React components.

Q: Do I need to manually close the connection after running Farcaster queries?

Always call mcpClient.close() once your stream completes. This prevents socket leaks and ensures your edge functions spin down cleanly after executing tools like listuserfollowingchannels.

Stream real-time Farcaster social graphs and live channel moderation directly into your Next.js UI using Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Farcaster (Decentralized Social Protocol) MCP to Vercel AI SDK

Create your Vinkius account to connect Farcaster (Decentralized Social Protocol) 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 Farcaster (Decentralized Social Protocol) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live channel moderation with Vercel AI SDK

Build real-time moderation dashboards where channel owners see actions happen live. Connect this MCP Server to your backend. Your agent calls `list_moderated_casts` to fetch recent actions and streams the raw event data directly to your React components without blocking the main thread. When a moderator hides a bad post, the tool `moderate_cast` executes in the background. The updated state streams straight to the UI, keeping the channel feed clean without requiring manual browser refreshes.

Render Farcaster follower graphs on the edge

Your agent uses `get_primary_address` and `list_account_verifications` to resolve on-chain identities. The Vercel AI SDK streams these verified credentials straight to your frontend, matching FIDs to Ethereum addresses instantly. Users can drill down into any community by querying `list_channel_followers`. The results render as they arrive, avoiding loading spinners while the agent maps out who follows whom across the decentralized network.

Direct channel actions from your interface

Let users join or leave communities directly through conversational inputs in your app. The agent triggers `follow_channel` or `unfollow_channel` on the fly, updating the user's subscription state in real-time. For channel admins, the agent can pin important announcements using `pin_cast`. This updates the UI state immediately, proving that your Next.js app handles decentralized actions as fast as a traditional web database using this MCP Server.

Setup guide

Set up Farcaster (Decentralized Social Protocol) 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 Farcaster (Decentralized Social Protocol) 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 Farcaster (Decentralized Social Protocol) 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 Farcaster. 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 Farcaster (Decentralized Social Protocol) 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 Farcaster (Decentralized Social Protocol) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and call `createMCPClient` with your HTTP endpoint. Pass the tools directly to `streamText` to let your agent call Farcaster tools like `list_all_channels` on demand.

Yes. Your agent can call `moderate_cast` to hide spam and immediately stream the updated action log back to your frontend. This keeps your interface in sync with the protocol state.

The agent calls tools like `get_current_fname_by_fid` and `list_account_verifications` during the generation loop. The SDK streams the resolved handle and verified wallets directly to your React components.

Always call `mcpClient.close()` once your stream completes. This prevents socket leaks and ensures your edge functions spin down cleanly after executing tools like `list_user_following_channels`.

Vinkius runs this MCP Server in an isolated V8 sandbox, meaning your private keys and session tokens never touch the LLM or client-side code. Your authenticated actions like `ban_channel_user` are signed inside a zero-trust environment, keeping your protocol identity safe.

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