Codex CCXT MCP MCP Server

io.github.lucyfox199818-collab/ccxt-mcp

Repository Registry

What is the Codex CCXT MCP MCP server?

Dry-run-first CCXT MCP with market, account, derivatives, and guarded trading tools.

How to install Codex CCXT MCP

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

BINANCE_API_KEY
secret
Optional Binance API key for private account data and explicitly enabled trading.
BINANCE_API_SECRET
secret
Optional Binance API secret.
CCXT_EXCHANGE_ID
CCXT exchange identifier.
CCXT_DEFAULT_TYPE
Default CCXT market type.
CCXT_SANDBOX
Use the exchange sandbox when supported.
CCXT_ENABLE_TRADING
Explicit live-trading permission gate. Keep false for read-only and dry-run use.
CCXT_DRY_RUN
Return simulated results for mutating tools instead of sending exchange actions.

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

{
  "mcpServers": {
    "ccxt-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/lucyfox199818-collab/ccxt-mcp:0.1.0"
      ],
      "env": {
        "BINANCE_API_KEY": "<YOUR_BINANCE_API_KEY>",
        "BINANCE_API_SECRET": "<YOUR_BINANCE_API_SECRET>",
        "CCXT_EXCHANGE_ID": "<YOUR_CCXT_EXCHANGE_ID>",
        "CCXT_DEFAULT_TYPE": "<YOUR_CCXT_DEFAULT_TYPE>",
        "CCXT_SANDBOX": "<YOUR_CCXT_SANDBOX>",
        "CCXT_ENABLE_TRADING": "<YOUR_CCXT_ENABLE_TRADING>",
        "CCXT_DRY_RUN": "<YOUR_CCXT_DRY_RUN>"
      }
    }
  }
}

Related MCP servers

io.github.lucyfuur94/webnav

Maintained

A zero-LLM MCP server that replays recorded site maps instead of re-exploring browser routes.

TypeScript

Apache-2.0

View repository →

io.github.ludmila-omlopes/youtube-video-analyzer

Maintained

MCP stdio server for analyzing YouTube videos with Google Gemini

TypeScript

MIT

View repository →

pyscn

Active

Python code quality analyzer: complexity, dead code, clones, coupling, and health scoring for AI agents.

1.0k

MIT

View repository →

Obsidian Vault MCP

Active

Local research workflow MCP: Zotero sources → MinerU extraction → Obsidian vault with structured analysis and traceable AI skills.

Python

MIT

View repository →

OmniScholar

Active

Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents.

Python

MIT

View repository →

io.github.lugdwei/AgentMesh

MCP delegation fallback for AI agents to discover capabilities, knowledge, tools, and collaborators.

View repository →