How to Use the CrowdTangle MCP in CrewAI

Deploy autonomous agent crews on CrowdTangle data. Let your CrewAI teams research, analyze, and report on social trends 24/7.

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 CrewAI

Create your Vinkius account to connect CrowdTangle to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign a Research & Analysis Crew

Split up the work between specialized agents. You can create a 'Researcher' agent equipped with `search_posts_by_keyword` to find content about a topic. It then passes the most relevant post IDs to an 'Analyst' agent, which uses `get_post_details` to do a deep dive on engagement. This is what CrewAI was built for. The agents use a shared context to pass information back and forth. The Researcher finds the needles; the Analyst examines them. They work together without you orchestrating every step.

Build a Viral Tracker MCP Server Crew

Set up a crew to spot and track viral content autonomously. A 'Scout' agent can run `get_top_performing_posts` every hour. When it finds a post with an unusually high score, it adds the post ID to the crew's shared context and flags it for investigation. A second 'Investigator' agent sees the flag and immediately gets to work. It uses `get_link_shares` to find out which accounts are spreading the post and reports its findings. This is a sequential pipeline in action, running completely on its own.

Run Continuous Account Monitoring

Create a team of agents to keep a constant watch on your social accounts. One agent's only job is to use `list_monitored_lists` to maintain an up-to-date list of accounts to watch. It passes this list to a 'Performance' agent. The Performance agent then cycles through the list, calling `get_account_leaderboard` for each one to track changes in engagement and rank over time. This creates a persistent, autonomous system for competitive analysis.

Setup guide

Set up CrowdTangle MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke CrowdTangle tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="CrowdTangle Analyst",
    goal="Access and analyze CrowdTangle data via MCP.",
    backstory="Expert analyst with direct CrowdTangle access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent CrowdTangle transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="CrowdTangle Analyst",
        goal="Access and analyze CrowdTangle data via MCP.",
        backstory="Expert analyst with direct CrowdTangle access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent CrowdTangle transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign different CrowdTangle tools to specialized agents. For example, give one agent `search_posts_by_keyword` and `list_recent_posts` for discovery, and another agent `get_post_details` for analysis. They collaborate to complete the task.

Yes, that's a primary use case for CrewAI. The first agent finds posts and puts their IDs into the shared context. The second agent can then access those IDs from the context and run its own tools on them.

You can, and you should. When defining your agent in CrewAI, you can use a `tool_filter` with the MCP Server connection. This lets you grant each agent only the specific tools it needs for its role, which is key to building effective, specialized crews.

Definitely. You can have a 'Watcher' agent that finds interesting links and a 'Tracker' agent whose sole purpose is to use the `get_link_shares` tool. The Watcher passes URLs to the Tracker, which then reports on who is sharing them.

Yes. Vinkius secures the connection, and your CrewAI agents never handle your actual API keys. Every operation, whether it's touching post content or follower counts, is stateless and runs in an ephemeral environment that leaves no trace.

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