Bybit MCP. Analyze live liquidity, funding rates, and OHLCV data.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Bybit MCP Server provides direct access to real-time cryptocurrency market data from Bybit. You get tickers, full orderbook depth, candlestick/OHLCV data across all timeframes, and perpetual contract metrics like funding rates and open interest.
It lets your AI client query complex crypto state information instantly, without needing an API key for public data.
What your AI agents can do
Get funding history
Retrieves the historical funding rates for perpetual crypto contracts, showing payments between long and short positions.
Get index price kline
Fetches candlestick data representing the composite index price across multiple exchanges.
Get instruments
Lists all available trading pairs and contract specifications (spot, linear, inverse, option) for Bybit.
Retrieves the current price, 24h volume metrics, and high/low range for any specified trading pair.
Fetches candlestick (OHLCV) data for specific timeframes across spot or derivatives markets using defined start and end timestamps.
Returns the current list of pending buy bids and sell asks, showing immediate liquidity levels for a given symbol.
Checks historical funding rates to determine how much long or short positions paid out over time, specifying linear or inverse contracts.
Gets the history of open interest for a derivatives contract, showing total net exposure at specific intervals.
Lists all available trading pairs and contracts (spot, linear, inverse, option) to determine what data is accessible.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Bybit MCP Server: 10 Tools for Crypto Market Data
These tools allow your AI client to interact with Bybit's core data streams. Use them to pull everything from current prices and order depth to historical klines and funding rates.
019d8421get funding history
Retrieves the historical funding rates for perpetual crypto contracts, showing payments between long and short positions.
019d8421get index price kline
Fetches candlestick data representing the composite index price across multiple exchanges.
019d8421get instruments
Lists all available trading pairs and contract specifications (spot, linear, inverse, option) for Bybit.
019d8421get kline
Gets standard candlestick data (OHLCV) for technical analysis across spot or derivatives markets over defined time intervals.
019d8421get mark price kline
Provides candlestick data specifically for the mark price, which is used by exchanges to calculate liquidations in derivatives contracts.
019d8421get open interest
Tracks the history of open interest levels for a specific derivatives contract over set time intervals.
019d8421get orderbook
Returns real-time price and quantity levels showing current market depth, listing both active buy bids and sell asks.
019d8421get recent trades
Lists the latest executed trades for a symbol, providing the price, size, side (Buy/Sell), and timestamp of every transaction.
019d8421get server time
Returns the current synchronized time from the Bybit server to ensure accurate request timing.
019d8421get tickers
Fetches real-time market prices and 24h metrics for any crypto pair across spot, linear, inverse, or option markets.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Bybit, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
When you connect your agent to the Bybit MCP Server, you get direct access to raw market state data. This isn't some fancy API wrapper; it gives your client tools that read the exchange’s current status instantly. You don't need an API key just to query public market flow.
Getting Real-Time Snapshots and Market Depth
The get_tickers tool fetches real-time pricing data for any crypto pair, giving you instant access to the current price, 24-hour volume metrics, and the high/low range. If you need to see what's actively waiting in the order book, get_orderbook returns a list of pending buy bids and sell asks, showing immediate liquidity levels for any given symbol.
The get_recent_trades tool lists every executed trade for a pair, giving you the price, size, side (Buy/Sell), and timestamp for each transaction.
Analyzing Price Movements Over Time
For calculating historical price series, you'll use get_kline, which fetches standard candlestick data (OHLCV) across spot or derivatives markets over defined time intervals. If you need to track the composite index price across multiple exchanges, get_index_price_kline handles that. The get_mark_price_kline tool provides specific candlestick data for the mark price—the figure exchanges use when calculating liquidations in derivatives contracts.
Deep Dive Into Derivatives Metrics
To understand the complexities of perpetual contracts, you've got specialized tools. You can check historical funding rates to see exactly how much long and short positions paid out over time; get_funding_history handles this for both linear and inverse contracts. For tracking total net exposure, get_open_interest gets the history of open interest levels for a derivatives contract at specific intervals.
The system also provides full metadata using get_instruments, which lists every available trading pair and contract specification—whether it's spot, linear, inverse, or options.
Utility and Timing
For accurate timing in your scripts, get_server_time returns the current synchronized time directly from the Bybit server. All this functionality means you can query complex crypto state information instantly. You'll know exactly what data streams are available for technical analysis or risk modeling without having to manually check documentation.
How Bybit MCP Works
- 1 First, initiate a conversation with your AI client, asking for specific market metrics (e.g., 'Show me the 1-hour klines for ETHUSDT').
- 2 Your agent maps this request to the appropriate tool and runs it against the Bybit server.
- 3 You get back structured data: either a list of recent trades, or an array of OHLCV candles ready for analysis.
The bottom line is you talk naturally, and your AI client converts that query into precise calls to market-specific tools, returning clean data structures.
Who Is Bybit MCP For?
This tool serves quant developers and algorithmic traders who hate relying on slow dashboard refreshes. It’s for the analyst stuck in a loop of cross-referencing multiple charts—the one who needs to know if orderbook depth supports a breakout before they write the execution script.
Runs background checks comparing get_open_interest changes against historical volatility (get_kline) to validate trading signals.
Uses get_instruments first, then feeds the resulting pair list into a script that calls get_tickers and get_orderbook to initialize bot parameters.
Compares spot prices (get_kline) against derivatives mark prices (get_mark_price_kline) to understand liquidation risk across different contracts.
What Changes When You Connect
- Instant Orderbook Depth: Instead of viewing static charts, you use
get_orderbookto see the real-time distribution of bids and asks. This gives immediate insight into where major buy/sell pressure is building up on any pair. - Full Technical Context: The
get_klinetool lets your agent pull historical OHLCV data for days, weeks, or minutes. You can instantly feed this time series data into a script for custom technical indicator calculation. - Derivatives Risk Mapping: By running
get_funding_history, you track the cost of carry across perpetual contracts. This tells you if longs are paying shorts—a key signal in crypto cycles. - Tracking Market Exposure: Use
get_open_interestto monitor total accumulated risk for a pair. A sudden spike or drop suggests major institutional positioning changes, giving context beyond just price movement. - Comprehensive Pair Discovery: You don't know the exact contract you need? Run
get_instruments. It lists all available pairs and their types (spot/linear/inverse), saving time before callingget_tickers.
Real-World Use Cases
Validating a potential breakout.
A trader notices the price is near an old support level. They ask their agent: 'What's the orderbook depth and recent trades for BTCUSDT right now?' The agent runs get_orderbook and get_recent_trades. If there’s a massive wall of bids (high depth) combined with sudden, large buy-side execution in get_recent_trades, they know institutional money is backing the breakout.
Comparing spot vs. derivatives price action.
An analyst wants to see if leveraged contracts are moving differently from the underlying asset. They use get_kline on the BTCUSDT spot pair and run it again using get_mark_price_kline for the perpetual contract. If the candles diverge, they know derivative positioning is detached from the core market.
Calculating potential liquidation risk.
A bot needs to determine the current total exposure in a pool of contracts. The developer runs get_open_interest and then cross-references that data with recent funding rate changes from get_funding_history. This lets them forecast how much capital is at risk.
Checking market health before deployment.
A developer needs to ensure their bot can handle all required pairs. They run get_instruments first. Once the list of symbols is confirmed, they iterate through them using get_tickers to pull the initial 24h metrics and confirm connectivity across the board.
The Tradeoffs
Asking for 'the best price'
User asks: 'What's a good time to buy BTC?' This vague query forces the agent to guess, often leading to irrelevant general advice instead of actionable data.
→
Be specific. Use get_tickers first to get current metrics, then use get_orderbook to see if there are immediate bids absorbing selling pressure. Always ground your questions in a tool call.
Ignoring timeframes
User asks: 'Show me the price movement.' Without specifying an interval, the agent might default to insufficient data or simply give a single point value that is useless for trend analysis.
→
Always specify intervals. Use get_kline and define your time range (e.g., 4-hour candles over the last week) rather than asking for 'the price'.
Treating spot data like derivatives data
User asks: 'What is the funding rate on ETHUSDT?' Spot pairs don't have funding rates. The agent fails or gives misleading information because they confused market types.
→
Confirm the contract type first using get_instruments. If you are checking perpetual contracts, always use specialized tools like get_funding_history.
When It Fits, When It Doesn't
Use this server if your task requires comparing multiple, distinct layers of market state information: price action (OHLCV), liquidity depth (Orderbook), and capital structure (Open Interest/Funding Rates). It’s built for deep quantitative analysis. Don't use it if you are doing basic fundamental research—if your query is 'Why did the Fed hike rates?' or 'What is the political impact of X?', this server won't help. For simple price checks, get_tickers works fine. But if you need to know why the price might be moving—is it due to high open interest accumulation or temporary orderbook imbalance?—this toolset provides the granular data points necessary to answer that 'why.'
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Having to switch between 5 different tabs just to compare market depth and recent trades is a massive time sink.
Right now, if you want to assess liquidity for BTCUSDT, you have to open the chart (for klines), then manually jump to the orderbook panel to see bids/asks, and finally check the trade log to see where the recent volume came from. It's three separate data points requiring multiple clicks and context switching.
With this MCP server, you ask your agent: 'Give me the current market depth and recent trades for BTCUSDT.' The agent runs `get_orderbook` and `get_recent_trades`. You get a single, structured output that correlates high-level liquidity with immediate transaction flow. No tabs needed.
The Bybit MCP Server gives you full control over market data structure.
Previously, if an analysis required both historical price action and current open interest, you had to run two separate API calls manually—one for `get_kline` (historical) and one for `get_open_interest` (current exposure). These were often treated as disconnected data streams.
Now, your agent can correlate them in a single workflow. You ask it to compare the 1-day open interest changes against the last five days of OHLCV candles. It connects the two tools, giving you one integrated view for decision-making.
Common Questions About Bybit MCP
How do I check real-time prices on Bybit using get_tickers? +
Just ask your agent to run get_tickers for the symbol you care about. It returns the current price, 24h high/low, and volume in one structured response.
Can I use get_kline for derivatives contracts? +
Yes. The get_kline tool supports both 'linear' and 'inverse' categories for candlestick data, letting you analyze the time series of perpetual futures or options.
What is the difference between get_orderbook and get_recent_trades? +
get_orderbook shows pending orders (the bids/asks waiting to be filled) that define market depth. get_recent_trades shows executed trades—the actual transactions that just happened.
Does get_funding_history cover all perpetual contracts? +
The tool covers funding rates for specified 'linear' or 'inverse' categories. You must specify the contract type when asking the agent to run get_funding_history.
Do I need an API key to use get_tickers? +
No. For public market data like tickers, klines, and orderbooks, you don't need a dedicated API key setup for your AI client to access the information.
What is the functional difference between using get_index_price_kline and get_mark_price_kline? +
The index price reflects a composite market value drawn from multiple exchanges. Mark price, however, is specifically calculated for determining liquidation risk within derivatives contracts.
When I use get_instruments, how do I filter for specific contract types like 'linear' versus 'inverse'? +
You pass the required category (e.g., "spot," "linear") as a parameter to the tool. This limits the returned list of pairs and contracts to only those matching your specified type.
Before running a historical query with get_kline, should I use get_server_time? +
Yes. Use get_server_time first. This ensures you grab the current system timestamp, guaranteeing that the start and end time parameters for your klines are perfectly synchronized with Bybit's clock.
Do I need an API key for market data? +
No! All public market data endpoints (tickers, klines, orderbook, trades, instruments, funding, open interest) are completely free and open. No authentication required.
What trading categories are available? +
Four categories: "spot" (spot trading), "linear" (USDT/USDC perpetual & futures), "inverse" (inverse perpetual & futures), "option" (options). Use get_instruments to see all available pairs.
What kline intervals are supported? +
Intervals: 1, 3, 5, 15, 30, 60, 120, 240, 360, 720 (minutes), D (daily), W (weekly), M (monthly). Up to 1000 candles per request.
What is funding rate? +
Funding rate is a periodic payment exchanged between long and short traders in perpetual futures. Positive rate means longs pay shorts. It keeps the perpetual price close to the spot price. Payments occur every 8 hours on Bybit.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Clearbit (HubSpot)
Enrich person and company data via Clearbit — track leads, monitor firmographics, and audit B2B intelligence directly from any AI agent.
Mashvisor
Analyze real estate investments — compare Airbnb vs traditional rental ROI via AI.
Bitly
Shorten and manage links via Bitly — track clicks, analyze metrics, and manage groups directly from any AI agent.
You might also like
Xiaomi Push Service / 小米推送
Xiaomi's essential device push platform — send notifications to MIUI and Global devices via AI.
GorillaDesk
Manage field service operations — schedule jobs, invoice customers, and update notes via AI.
DecileHub
Segment your customers by value and behavior with predictive analytics that reveal your most profitable audience segments.