How to Use the CoinCap MCP in LlamaIndex

Q: Can LlamaIndex store historical CoinCap data in a vector database?

Yes. You can fetch historical candlestick data using getcandles and load the resulting JSON documents directly into your index pipeline for vector storage.

Q: Can I filter which market assets are visible to the agent?

Yes. You can use listassets with specific search queries and limits to restrict the data your agent retrieves, keeping your token usage down.

Index live CoinCap cryptocurrency prices and exchange data directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CoinCap MCP to LlamaIndex

Create your Vinkius account to connect CoinCap 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 CoinCap with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground LlamaIndex RAG in Real-Time Crypto Data

Stop letting your financial LLMs hallucinate token prices. By connecting this MCP Server to your LlamaIndex setup, your agent uses `get_asset` and `get_rate` to fetch real-time market data during query execution, ensuring your index stays accurate. The retrieved raw numbers are injected straight into your context window. This means your query engine answers questions about current market caps and circulating supplies using actual, verified data instead of outdated weights.

Index Historical Market Candles for Semantic Search

You can query past market trends by indexing raw historical snapshots from `get_asset_history` and `get_candles` into your vector database. LlamaIndex parses these historical data points so your agent can perform semantic searches over past market behavior. This turns raw OHLCV JSON payloads into searchable knowledge. Your agent can compare current market patterns with historical intervals to find similar trends without manual data formatting.

Build Searchable Knowledge Bases of Crypto Exchanges

Use `get_exchange` and `list_exchanges` to build a dynamic directory of trading venues inside your index. Your LlamaIndex agent can quickly look up which exchanges are verified and check their 24-hour trading volumes. By combining this with `get_markets`, your system maps out trading pairs across different platforms. The agent can then answer complex structural questions about market liquidity and exchange rankings.

Setup guide

Set up CoinCap 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 CoinCap 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 CoinCap tools.",
)
response = await agent.run("List recent CoinCap 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 CoinCap. 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 CoinCap 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 CoinCap MCP in LlamaIndex

Install llama-index-tools-mcp and initialize the client. Wrap it in a McpToolSpec to convert the CoinCap tools into a list that your FunctionAgent can use.

Yes. You can fetch historical candlestick data using get_candles and load the resulting JSON documents directly into your index pipeline for vector storage.

Yes. The tool spec maps the server's endpoints to executable tools, allowing your agent to dynamically fetch asset profiles and exchange rates during query synthesis.

Yes. You can use list_assets with specific search queries and limits to restrict the data your agent retrieves, keeping your token usage down.

No. This server only processes public market data requests like asset rates and exchange lists. Your vector database, query embeddings, and indexed documents remain completely isolated within your local environment.

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