How to Use the CrowdTangle MCP in Mastra AI

Q: How can Mastra AI build a workflow to find top CrowdTangle posts?

You'd use the gettopperformingposts tool as the first step in your Mastra AI agent. Then, you can use the workflow engine to process the results, like sending a notification or triggering another tool if a post's score is high.

Q: Does Mastra AI support human approval for CrowdTangle actions?

Yes, Mastra AI has a requireToolApproval option. You can configure your agent to pause and wait for a human to approve a step before it proceeds, which is useful for workflows that might take a significant action based on social data.

Q: Can I get my CrowdTangle account details with a Mastra agent?

Absolutely. The getaccountdetails tool gives your agent access to your dashboard settings and API rate limits. It's a good first step in a workflow to make sure you have enough quota before running a large job.

Build resilient social media monitoring workflows. Connect CrowdTangle to Mastra AI to create bots that don't break.

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 Mastra AI

Create your Vinkius account to connect CrowdTangle to Mastra 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 CrowdTangle with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Social Media Reporting

Set up a Mastra AI agent to automatically pull social media activity. It can use `list_recent_posts` to get a feed of new content and then loop through the results, calling `get_post_details` on each one to gather deep engagement metrics for your database. Here's the thing: network requests fail. Mastra AI is built for that. If a call to the CrowdTangle API times out, your agent won't crash. It automatically retries with exponential backoff, ensuring your workflow finishes the job.

Create Conditional Workflows with Mastra AI

Your agent can make decisions based on CrowdTangle data. For instance, it can run `get_top_performing_posts` daily. If a post's score exceeds a threshold you set, the agent can then trigger other tools, like `get_link_shares`, to investigate why it's going viral. This if-then logic is a core part of the Mastra AI framework. You define the steps and conditions, and the agent executes the workflow. It's how you move from simple data fetching to building an intelligent process.

Deploy Monitoring Agents in One Command

Build a workflow that manages your tracking lists. An agent could use `search_tracking_lists` to find a specific list by name, then pass its ID to `get_account_leaderboard` to generate a performance report. You can chain these tools together to create complex reporting jobs. Once your agent's logic is defined, you can deploy it to any cloud environment with a single command. Mastra AI packages everything for you, turning your social media monitoring concept into a production-ready service.

Setup guide

Set up CrowdTangle MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All CrowdTangle tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "crowdtangle-mcp-client",
  servers: {
    "crowdtangle-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "CrowdTangle Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to CrowdTangle tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent CrowdTangle transactions"
);
console.log(result.text);

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 Mastra AI

You'd use the `get_top_performing_posts` tool as the first step in your Mastra AI agent. Then, you can use the workflow engine to process the results, like sending a notification or triggering another tool if a post's score is high.

Yes, Mastra AI has a `requireToolApproval` option. You can configure your agent to pause and wait for a human to approve a step before it proceeds, which is useful for workflows that might take a significant action based on social data.

Mastra AI automatically handles transient failures. It will retry the API call with exponential backoff, so your workflow can recover from temporary network issues or API rate limiting without you writing any custom retry logic.

Absolutely. The `get_account_details` tool gives your agent access to your dashboard settings and API rate limits. It's a good first step in a workflow to make sure you have enough quota before running a large job.

It is. Each tool your Mastra AI agent calls runs in a completely isolated sandbox on Vinkius. That sandbox, along with any data like account rankings or post content, is destroyed the moment the call is finished. Nothing is logged or stored.

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