How to Use the CrowdTangle MCP in LangChain

Build ReAct agents that track viral social media trends using LangChain and MCP.

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 LangChain

Create your Vinkius account to connect CrowdTangle to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Wire CrowdTangle into LangChain MCP setups

Your agent needs real-world social data to make decisions. Connecting this MCP Server gives your ReAct setups direct access to Facebook and Instagram metrics. They call `search_posts_by_keyword` to find trending topics, then feed that output into downstream LLM prompts. That means you stop writing custom API wrappers. The agent decides when to fire off `get_top_performing_posts` based on the context of the user's question. It reads the actual vs expected interaction scores and passes the raw data to the next link in your chain.

Multi-step reasoning for social tracking

Simple queries fail when investigating complex social campaigns. You need an agent that plans its approach. It starts by pulling your tracked groups with `list_monitored_lists`. The system executes `get_account_leaderboard` to figure out which pages drive the highest average engagement rates once it knows the target lists. You get a complete analytical workflow without hardcoding the steps.

Full observability with LangSmith

Debugging API calls inside an agent loop sucks. Because these tools run through standard adapters, every request logs directly to your tracing backend. You see exactly what inputs the agent sent to `get_link_shares`. Latency spikes become obvious immediately. If `get_post_details` takes too long pulling reaction breakdowns, you spot it in the trace. Developers know exactly how many tokens their agent burned parsing the social metadata.

Setup guide

Set up CrowdTangle MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes CrowdTangle tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "crowdtangle-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent CrowdTangle transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the langchain-mcp-adapters package. Initialize a MultiServerMCPClient with your Vinkius endpoint URL and pass the resulting tools to your agent constructor.

Yes. You handle caching at the framework level. Wrap the tool calls in a standard cache layer to avoid hitting the endpoint limits repeatedly.

That is the primary use case. The agent reads the tool descriptions and autonomously decides when to pull social data.

The connection is stateless by default. You must use client.session() to maintain persistent context across multiple requests.

Your API rate limits and dashboard settings stay isolated. The `get_account_details` tool reads workspace configuration boundaries, but your local environment only processes the exact JSON returned from the Vinkius sandbox.

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