Skip to main content
Glama
enesjakozh
esshka

OKX MCP Server

by esshka
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

OKX MCP Server

A Model Context Protocol server that provides real-time cryptocurrency price data from OKX exchange.

Features

This MCP server connects to the OKX API to provide cryptocurrency price information through a simple tool interface. It includes comprehensive error handling, request logging, and rate limiting via OKX's API.

Tools

get_candlesticks

Retrieves historical candlestick (OHLCV) data for any instrument on OKX.

  • Input:

    • instrument: String (required) - Instrument ID (e.g. "BTC-USDT")

    • bar: String (optional) - Time interval (e.g. "1m", "5m", "1H", "1D"), default "1m"

    • limit: Number (optional) - Number of candlesticks to return (max 100), default 100

  • Output: Array of JSON objects, each containing:

    • timestamp: ISO timestamp of the candlestick

    • open: Opening price

    • high: Highest price

    • low: Lowest price

    • close: Closing price

    • volume: Trading volume

    • volumeCurrency: Volume in currency terms

Example usage:

[
  {
    "timestamp": "2025-03-07T17:00:00.000Z",
    "open": "87242.8",
    "high": "87580.2",
    "low": "86548.0",
    "close": "87191.8",
    "volume": "455.72150427",
    "volumeCurrency": "39661166.242091111"
  }
]

get_price

Fetches the latest price and 24-hour market data for any instrument on OKX.

  • Input:

    • instrument: String (required) - Instrument ID (e.g. "BTC-USDT")

  • Output: JSON object containing:

    • instrument: The requested instrument ID

    • lastPrice: Latest trade price

    • bid: Current best bid price

    • ask: Current best ask price

    • high24h: 24-hour high price

    • low24h: 24-hour low price

    • volume24h: 24-hour trading volume

    • timestamp: ISO timestamp of the data

Example usage:

{
  "instrument": "BTC-USDT",
  "lastPrice": "65432.1",
  "bid": "65432.0",
  "ask": "65432.2",
  "high24h": "66000.0",
  "low24h": "64000.0",
  "volume24h": "1234.56",
  "timestamp": "2024-03-07T17:22:28.000Z"
}

Related MCP server: OKX MCP Server

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop or VSCode, add the server config to your MCP settings:

macOS (VSCode):

~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

macOS (Claude Desktop):

~/Library/Application Support/Claude/claude_desktop_config.json

Windows (VSCode):

%APPDATA%/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

Windows (Claude Desktop):

%APPDATA%/Claude/claude_desktop_config.json

Configuration:

{
  "mcpServers": {
    "okx": {
      "command": "node",
      "args": ["/path/to/okx-mcp-server/build/index.js"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

Error Handling

The server implements comprehensive error handling:

  • Network errors are captured and returned with context

  • Invalid instrument IDs return appropriate error messages

  • API rate limits are respected through axios timeout configuration

  • All errors are logged for debugging purposes

Available Tools

2 tools
get_candlesticksC

Get candlestick data for an OKX instrument

ParametersJSON Schema
NameRequiredDescriptionDefault
instrumentYesInstrument ID (e.g. BTC-USDT)
barNoTime interval (e.g. 1m, 5m, 1H, 1D)1m
limitNoNumber of candlesticks (max 100)

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure but only states what the tool does without mentioning rate limits, authentication needs, response format, or pagination behavior. It doesn't explain what 'candlestick data' includes (e.g., OHLC values) or any constraints beyond the implied data retrieval.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without any unnecessary words. It's front-loaded and appropriately sized for a simple data retrieval tool, with every word contributing to clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete for a tool with three parameters. It doesn't cover behavioral aspects like response format, error handling, or usage context, leaving significant gaps for an AI agent to understand how to effectively invoke and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all three parameters. The description adds no additional meaning beyond the schema, such as explaining the significance of candlestick intervals or instrument IDs in context. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('candlestick data for an OKX instrument'), making the purpose immediately understandable. However, it doesn't differentiate from the sibling tool 'get_price', which likely provides different market data, leaving room for improvement in distinguishing between similar data retrieval functions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus the sibling 'get_price' or any alternatives. It lacks context about when candlestick data is appropriate (e.g., for charting, technical analysis) versus price data, offering no usage boundaries or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_priceC

Get latest price for an OKX instrument

ParametersJSON Schema
NameRequiredDescriptionDefault
instrumentYesInstrument ID (e.g. BTC-USDT)

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but lacks details on traits like rate limits, authentication needs, error handling, or response format. This is a significant gap for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It is appropriately sized and front-loaded, clearly stating the tool's purpose without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain behavioral traits, return values, or usage context, which are essential for a tool that fetches financial data. This leaves clear gaps in understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents the 'instrument' parameter. The description adds no additional meaning beyond what the schema provides, such as examples or constraints, meeting the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and resource 'latest price for an OKX instrument', making the purpose specific and understandable. It doesn't explicitly distinguish from the sibling 'get_candlesticks', which provides historical price data, so it misses full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'get_candlesticks'. There is no mention of prerequisites, context, or exclusions, leaving usage unclear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • Addedget_candlesticks
    • Addedget_price
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 2 tools

Disambiguation4/5

The two tools have distinct purposes: get_candlesticks retrieves historical price data in candlestick format, while get_price fetches the latest price. There is minimal overlap as they target different data types (historical vs. current), though both relate to instrument pricing which could cause slight confusion in some contexts.

Naming Consistency5/5

Both tools follow a consistent verb_noun naming pattern (get_candlesticks, get_price) with clear, descriptive names. The snake_case style is uniform throughout, making the tools easy to identify and predict.

Tool Count2/5

With only 2 tools, the server feels severely under-scoped for a financial trading platform like OKX. This minimal set lacks essential operations such as placing orders, managing accounts, or accessing market depth, which are core to trading workflows.

Completeness2/5

The tool surface is highly incomplete for an OKX server, covering only price data retrieval. There are significant gaps in trading functionality (e.g., no create_order, cancel_order), account management, or market data beyond basic prices, which will likely cause agent failures in typical trading scenarios.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Bybit MCP Server

    sammcj
    A
    license
    B
    quality
    F
    maintenance
    A Model Context Protocol server that provides read-only access to Bybit's cryptocurrency exchange API, allowing users to query real-time cryptocurrency data using natural language.
    12
    11 npm
    16
    MIT

  • OKX MCP Server

    badger3000
    A
    license
    B
    quality
    D
    maintenance
    Provides real-time and historical cryptocurrency price data from the OKX exchange, including live WebSocket updates, candlestick charts, and visual price analysis for trading pairs.
    5
    7 npm
    3
    MIT

  • Tastytrade MCP Server

    tnngnc
    F
    license
    B
    quality
    D
    maintenance
    Provides access to Tastytrade historical price data via the Model Context Protocol. It enables users to retrieve historical candle data for specific financial symbols and time intervals.
    1
    -

Appeared in Searches