How to Use the CrowdTangle MCP in LlamaIndex

Q: Can LlamaIndex filter which CrowdTangle tools the agent sees?

Yes. You apply an allowedtools filter when configuring the spec. This prevents the agent from calling expensive endpoints unnecessarily.

Q: Does LlamaIndex support indexing the CrowdTangle MCP Server output?

That is exactly how it works. Set includeresources=True and the framework will treat the API responses as indexable documents.

Index viral social media posts directly into LlamaIndex vector stores using 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 LlamaIndex

Create your Vinkius account to connect CrowdTangle to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn social feeds into queryable RAG data

Most RAG applications rely on static PDFs. Connecting this MCP Server lets your LlamaIndex pipelines ingest live social media metrics. Your agent runs `list_recent_posts` and immediately chunks the captions and engagement stats. Those chunks go straight into your vector store. When a user asks about recent brand sentiment, the query engine refuses to guess. It retrieves the exact platform identifiers and comment counts pulled from the API.

Ground your LlamaIndex agents in API reality

Hallucinations happen when LLMs lack hard data. Give your FunctionAgent access to `list_media_posts` and it can ground its answers in actual photo and video URLs. The framework pulls the metadata and indexes it on the fly. If you need to audit your own setup, the agent calls `get_account_details` to read your API limits and workspace configs. That returns answers based on your exact dashboard state.

Semantic search across tracked accounts

Keyword matching misses the nuance of social campaigns. Your pipeline can execute `search_tracking_lists` to pull list metadata, then embed those results for semantic search. Because it uses an MCP connection, finding out who amplified a message becomes a simple query. The agent calls `get_link_shares` to find follower counts and interaction totals. We throw that data into the index so you can ask natural language questions about the spread.

Setup guide

Set up CrowdTangle MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all CrowdTangle MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to CrowdTangle tools.",
)
response = await agent.run("List recent CrowdTangle data")

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 LlamaIndex

Install llama-index-tools-mcp. Use BasicMCPClient to connect to the endpoint, then pass it to McpToolSpec to generate the async tool list.

Yes. You apply an allowed_tools filter when configuring the spec. This prevents the agent from calling expensive endpoints unnecessarily.

That is exactly how it works. Set include_resources=True and the framework will treat the API responses as indexable documents.

Standard clients require custom parsing logic for every endpoint. The protocol standardizes the schema so your query engine understands the inputs and outputs immediately.

Vector stores only index the specific fields you request. When calling `get_post_details`, the reaction breakdowns and share history stay confined to your local database and the ephemeral 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