CrowdTangle MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect CrowdTangle through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="CrowdTangle Assistant",
instructions=(
"You help users interact with CrowdTangle. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from CrowdTangle"
)
print(result.final_output)
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.
The OpenAI Agents SDK auto-discovers all 10 tools from CrowdTangle through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries CrowdTangle, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
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 OpenAI Agents SDK 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 OpenAI Agents SDK via MCP
Follow these steps to integrate the CrowdTangle MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from CrowdTangle
Why Use OpenAI Agents SDK with the CrowdTangle MCP Server
OpenAI Agents SDK provides unique advantages when paired with CrowdTangle through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
CrowdTangle + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the CrowdTangle MCP Server delivers measurable value.
Automated workflows: build agents that query CrowdTangle, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries CrowdTangle, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through CrowdTangle tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query CrowdTangle to resolve tickets, look up records, and update statuses without human intervention
CrowdTangle MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect CrowdTangle to OpenAI Agents SDK 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 OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK 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 OpenAI Agents SDK
Common issues when connecting CrowdTangle to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
CrowdTangle + OpenAI Agents SDK FAQ
Common questions about integrating CrowdTangle MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
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 OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.