CrowdTangle MCP Server for LangChain 10 tools — connect in under 2 minutes
LangChain is the leading Python framework for composable LLM applications. Connect CrowdTangle through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MultiServerMCPClient({
"crowdtangle": {
"transport": "streamable_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,
)
response = await agent.ainvoke({
"messages": [{
"role": "user",
"content": "Using CrowdTangle, show me what tools are available.",
}]
})
print(response["messages"][-1].content)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About CrowdTangle MCP Server
Integrate CrowdTangle, the public insights tool from Meta, directly into your AI workflow. Monitor social media trends, track how links are being shared across platforms, and identify high-performing content using natural language.
LangChain's ecosystem of 500+ components combines seamlessly with CrowdTangle through native MCP adapters. Connect 10 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.
What you can do
- Post Monitoring — List and search for recent public posts on Facebook, Instagram, and other supported platforms.
- Viral Discovery — Identify overperforming and viral content based on actual vs. expected interaction.
- Link Tracking — See which public accounts and pages have shared specific URLs.
- Leaderboards & Lists — Monitor account leaderboards and manage your custom tracking lists.
The CrowdTangle MCP Server exposes 10 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect CrowdTangle to LangChain via MCP
Follow these steps to integrate the CrowdTangle MCP Server with LangChain.
Install dependencies
Run pip install langchain langchain-mcp-adapters langgraph langchain-openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save the code and run python agent.py
Explore tools
The agent discovers 10 tools from CrowdTangle via MCP
Why Use LangChain with the CrowdTangle MCP Server
LangChain provides unique advantages when paired with CrowdTangle through the Model Context Protocol.
The largest ecosystem of integrations, chains, and agents. combine CrowdTangle MCP tools with 500+ LangChain components
Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step
LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging
Memory and conversation persistence let agents maintain context across CrowdTangle queries for multi-turn workflows
CrowdTangle + LangChain Use Cases
Practical scenarios where LangChain combined with the CrowdTangle MCP Server delivers measurable value.
RAG with live data: combine CrowdTangle tool results with vector store retrievals for answers grounded in both real-time and historical data
Autonomous research agents: LangChain agents query CrowdTangle, synthesize findings, and generate comprehensive research reports
Multi-tool orchestration: chain CrowdTangle tools with web scrapers, databases, and calculators in a single agent run
Production monitoring: use LangSmith to trace every CrowdTangle tool call, measure latency, and optimize your agent's performance
CrowdTangle MCP Tools for LangChain (10)
These 10 tools become available when you connect CrowdTangle to LangChain via MCP:
get_account_details
Touches dashboard settings, API rate limits, and workspace configuration boundaries. Retrieve metadata for your CrowdTangle account
get_account_leaderboard
Resolves account rankings, total interactions, and average engagement rates. Get engagement leaderboard for accounts in your lists
get_link_shares
Resolves which tracked accounts shared the link, their follower counts, and total interactions generated per share. See which accounts have shared a specific URL
get_post_details
Touches reaction breakdowns, share history, and platform-specific metadata boundaries. Get full engagement details for a specific post ID
get_top_performing_posts
Resolves "score" metrics (actual vs expected interactions) and associated social media metadata. Get the highest performing posts based on actual vs. expected interaction
list_media_posts
Resolves media URLs, content types (Photo, Video), and associated post captions. List recent posts that contain photos or videos
list_monitored_lists
Resolves list IDs, names, platform affiliations, and the number of accounts within each list. List all account lists you are tracking
list_recent_posts
Resolves post content, platform identifiers (Facebook, Instagram, etc.), account names, and engagement metrics (likes, shares, comments). List recent social media posts tracked by CrowdTangle
search_posts_by_keyword
Resolves relevant posts, associated accounts, and comparative performance data. Search for posts across platforms using a keyword
search_tracking_lists
Resolves list metadata matching the specified title filter. Search for specific tracking lists by title
Example Prompts for CrowdTangle in LangChain
Ready-to-use prompts you can give your LangChain agent to start working with CrowdTangle immediately.
"Search for recent viral posts about 'Electric Vehicles' on Instagram."
"Who has shared the link 'https://vinkius.com/blog/mcp-server' recently?"
"Show me the engagement leaderboard for my 'Competitors' list."
Troubleshooting CrowdTangle MCP Server with LangChain
Common issues when connecting CrowdTangle to LangChain through the Vinkius, and how to resolve them.
MultiServerMCPClient not found
pip install langchain-mcp-adaptersCrowdTangle + LangChain FAQ
Common questions about integrating CrowdTangle MCP Server with LangChain.
How does LangChain connect to MCP servers?
langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.Which LangChain agent types work with MCP?
Can I trace MCP tool calls in LangSmith?
Connect CrowdTangle with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect CrowdTangle to LangChain
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.