How to Use the CrowdTangle MCP in AutoGen

Q: How do I initialize CrowdTangle MCP tools in AutoGen?

Install the autogen-extmcp package. Use mcpservertools with your endpoint URL and pass the resulting list directly to your agent's constructor.

Q: What are the data privacy implications for this integration?

Your agents operate in a zero-trust environment. While getaccountdetails touches workspace configuration boundaries, the actual data transfer happens inside a secure V8 isolate that destroys itself after the run.

Build AutoGen agent teams that debate social media performance and viral trends via 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 AutoGen

Create your Vinkius account to connect CrowdTangle to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate over social metrics

Single-prompt analysis usually misses the bigger picture. By attaching this MCP Server to your AutoGen setup, you create distinct agents that argue over campaign results. A data-gatherer agent pulls the raw stats using `get_top_performing_posts`. A critic agent then reviews those actual versus expected interaction scores. It might challenge the initial findings, forcing the first agent to run `get_account_leaderboard`. That proves which accounts actually drove the engagement.

Consensus-driven AutoGen workflows

Complex public relations events require deliberation. You assign one agent to monitor brand safety by running `search_posts_by_keyword` across platforms. If it flags a negative trend, a strategy agent jumps in. The system executes `list_monitored_lists` to identify which of your tracked groups are exposed to the controversy. They negotiate a response plan based on the combined API data.

Automated schema conversion

Microsoft's framework handles the plumbing for you. Because it relies on the MCP standard, the McpToolAdapter automatically translates the endpoint schemas into formats your AssistantAgent understands natively. You just pass the URL to the server parameters. When an agent decides to investigate a viral URL, it calls `get_link_shares`. Nobody has to write a single line of type-checking code for the follower counts.

Setup guide

Set up CrowdTangle MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes CrowdTangle tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="CrowdTangle_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CrowdTangle data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="CrowdTangle_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CrowdTangle data")
    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 AutoGen

Install the autogen-ext[mcp] package. Use mcp_server_tools with your endpoint URL and pass the resulting list directly to your agent's constructor.

Yes. You map the tools to specific agents in your team. A researcher can have access while a summary agent does not.

The framework supports streamable HTTP transports natively. Your agents receive the social media data as soon as the sandbox processes the request.

They read the error message and try again. If a keyword search fails, the agent will rewrite the query and make another call automatically.

Your agents operate in a zero-trust environment. While `get_account_details` touches workspace configuration boundaries, the actual data transfer happens inside a secure V8 isolate that destroys itself after the run.

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