How to Use the CrowdTangle MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to get specific CrowdTangle post details?

You give your agent the getpostdetails tool. When you provide a post ID, it will return the full engagement data, including reaction breakdowns and share history, which you can then stream into your UI.

Q: Can my Vercel AI SDK app search my CrowdTangle tracking lists?

Yes, it can. The searchtrackinglists tool lets your agent find specific lists by their title. This is useful for building UIs where users need to select a list before running a report.

Q: What's the best way to show a CrowdTangle leaderboard with the Vercel AI SDK?

Use the getaccountleaderboard tool. The Vercel AI SDK is built for this — you can stream the ranking data directly into a table or list component in your app, so it updates live as the data arrives.

Q: How do I find recent posts that contain media?

The listmediaposts tool is what you're looking for. It returns a list of recent posts that specifically contain photos or videos, along with their media URLs and captions.

Stream CrowdTangle data directly into your Vercel AI SDK app's UI. Your users see live social stats, not loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CrowdTangle MCP to Vercel AI SDK

Create your Vinkius account to connect CrowdTangle 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 CrowdTangle with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Social Dashboards

Give your agent access to CrowdTangle's performance metrics. You can pull rankings with `get_account_leaderboard` or identify top content using the scoring from `get_top_performing_posts`. This is the raw data you need to build a real-time dashboard tracking social engagement. With the Vercel AI SDK, tool results stream directly into your React or Next.js components. As your agent gets the data, your UI updates piece by piece. The result is a dashboard that feels alive, with numbers and lists appearing instantly without a single loading state.

Track Link Shares with the Vercel AI SDK

Find out who is sharing a specific URL and how much traction it's getting. The `get_link_shares` tool tells you exactly which tracked accounts shared a link and the interactions each share generated. You can also cast a wider net with `search_posts_by_keyword` to find conversations around a topic. This is perfect for building user-facing tools that monitor brand mentions or track a story's viral spread. Because the AI SDK streams results, your user can watch the list of shares populate in real time, turning data discovery into a live event.

Manage Account Lists and Settings

This MCP Server also covers the administrative side of CrowdTangle. Your agent can pull all your tracked lists with `list_monitored_lists` or check your current API rate limits and workspace info using `get_account_details`. It's everything you need for building internal admin panels. Even for internal tools, the instant feedback from the Vercel AI SDK makes a difference. When you ask your agent to fetch a list, it doesn't just dump a wall of text after a delay. The list appears on screen as it's being fetched, making the interface feel fast and responsive.

Setup guide

Set up CrowdTangle 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 CrowdTangle 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 CrowdTangle 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 CrowdTangle. 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 CrowdTangle 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 CrowdTangle MCP in Vercel AI SDK

You give your agent the `get_post_details` tool. When you provide a post ID, it will return the full engagement data, including reaction breakdowns and share history, which you can then stream into your UI.

Yes, it can. The `search_tracking_lists` tool lets your agent find specific lists by their title. This is useful for building UIs where users need to select a list before running a report.

Use the `get_account_leaderboard` tool. The Vercel AI SDK is built for this — you can stream the ranking data directly into a table or list component in your app, so it updates live as the data arrives.

The `list_media_posts` tool is what you're looking for. It returns a list of recent posts that specifically contain photos or videos, along with their media URLs and captions.

Yes, your data is isolated. Vinkius processes each tool call in an ephemeral, zero-trust sandbox that's destroyed immediately after. The server only handles post content and engagement metrics, and your auth is managed by a single Vinkius token, not stored credentials.

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