How to Use the Bybit MCP in CrewAI

Q: How do I add Bybit tools to a CrewAI agent?

Pass your Vinkius HTTP endpoint directly into the agent's mcps array during initialization to connect to the MCP server. CrewAI automatically discovers tools like gettickers and exposes them to the agent.

Q: Can I limit which Bybit tools a CrewAI agent can use?

Yes, use MCPServerHTTP from the MCP module in crewai along with a toolfilter to expose only specific tools like getorderbook to your crew.

Equip your CrewAI agent teams with real-time Bybit market intelligence.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bybit MCP to CrewAI

Create your Vinkius account to connect Bybit 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 Bybit with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Divide and conquer market analysis with CrewAI

The `get_tickers` tool provides real-time market tickers across spot and futures. In a CrewAI setup, your researcher agent can pull this pricing data and pass it to your analyst agent for instant evaluation. This division of labor keeps your operations autonomous. While one agent monitors the overall market trend, another uses `get_open_interest` to track open positions on perpetual contracts, keeping the entire crew updated.

Monitor liquidation risks using an MCP Server

The `get_mark_price_kline` tool tracks historical mark prices used for liquidation calculations. Your risk-monitoring crew agent can check these price trends to flag potential liquidation zones for active contracts. By delegating this task to a specialized agent, your main execution agent can focus on tracking orderbooks via `get_orderbook`. CrewAI schedules these checks sequentially to keep your risk profiles fresh.

Filter trading pairs across multiple contracts

The `get_instruments` tool pulls active trading pairs filtered by symbol or base coin. Your discovery agent uses this list to scan for newly listed assets or high-volume pairs on Bybit. Once the discovery agent identifies a target, it hands the symbol over to the analysis agent to fetch candlestick trends via `get_kline`. This multi-agent pipeline operates entirely in the background without manual intervention.

Setup guide

Set up Bybit 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 Bybit tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Bybit 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="Bybit Analyst",
        goal="Access and analyze Bybit data via MCP.",
        backstory="Expert analyst with direct Bybit access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Bybit 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 Bybit. 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 Bybit 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 Bybit MCP in CrewAI

Pass your Vinkius HTTP endpoint directly into the agent's `mcps` array during initialization to connect to the MCP server. CrewAI automatically discovers tools like `get_tickers` and exposes them to the agent.

Yes, use `MCPServerHTTP` from the MCP module in crewai along with a `tool_filter` to expose only specific tools like `get_orderbook` to your crew.

Your crew executes tasks sequentially or hierarchically. A researcher agent fetches data using `get_funding_history`, then passes the raw rates to an analyst agent.

This server supports stdio, SSE, and Streamable HTTP protocols, allowing your Python-based crew to connect over whichever transport fits your deployment.

Vinkius processes all Bybit queries in ephemeral, zero-trust MCP sandboxes. Your market data, trade history searches, and pricing queries are never saved or exposed to other users.

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