Skip to main content
Glama
tradeos-mcp

tradeos-mcp

Official
by TradeOS-AI

tradeos-skills

Claude Code plugin for TradeOS: agentic technical analysis of XAUUSD and other markets, plus no-code AI trading agents for 24/7 smart alerts. Includes the /tradeos:analyze skill, ticker search, spread comparisons, and macro/news context.

Follows the Claude Code plugins guide and community marketplace submission.

Connect TradeOS after installation

In Claude, open Settings → Connectors, find TradeOS, enable it if it is off, click Connect, and sign in. In Claude Code, run /mcp, select tradeos, choose Connect, and complete sign-in. If you cannot find a TradeOS tool, first check that the connector is enabled. If a tool returns unauthorized, connect or reconnect and sign in, then retry your request.

Related MCP server: IBKR TWS MCP Server

Plugin layout

tradeos-mcp/                    ← plugin root (not inside .claude-plugin/)
├── .claude-plugin/
│   └── plugin.json             # manifest only
├── .mcp.json                   # MCP: Streamable HTTP + OAuth
├── logo.png                    # Plugin icon
├── LICENSE                     # MIT license
├── skills/
│   └── analyze/
│       └── SKILL.md            # /tradeos:analyze
└── README.md

File

Role

.claude-plugin/plugin.json

Plugin identity (name: tradeos), version, MCP wiring

.mcp.json

https://ai.tradeos.xyz/api/agent/mcp/mcp-call

logo.png

Plugin icon

LICENSE

MIT license

skills/analyze/SKILL.md

Tool picker + workflows for TradeOS MCP

Do not put skills/, .mcp.json, etc. inside .claude-plugin/ — only plugin.json belongs there.

Plugin icon: TradeOS logo. Privacy policy: TradeOS privacy policy.


Local development

From the repo root:

claude --plugin-dir .

In Claude Code:

  1. Enable the plugin if prompted.

  2. Run /mcp, connect tradeos, and complete sign-in.

  3. Run /reload-plugins after editing SKILL.md or plugin.json.

  4. Try the skill: /tradeos:analyze (namespace = plugin.json → name).

  5. Confirm MCP tools with mcp_health or /mcp.

Optional: scaffold-style init for personal copy:

claude plugin init my-tradeos   # creates ~/.claude/skills/my-tradeos/ — use as reference only

Validate before submit

From the plugin root (repo root):

claude plugin validate .

Fix any reported issues. The community review pipeline runs the same check plus automated safety screening.


Submit to the community marketplace

Anthropic hosts two public marketplaces (docs):

Marketplace

Notes

claude-plugins-official

Anthropic-curated; no public application

claude-community

Third-party plugins after review → @claude-community

Submission steps

  1. Run claude plugin validate . locally (from the repo root).

  2. Submit via one of:

  3. After approval, the plugin is pinned in anthropics/claude-plugins-community (catalog: marketplace.json).

  4. Public catalog syncs nightly — there may be a delay before install works.

Users install from community marketplace

/plugin marketplace add anthropics/claude-plugins-community
/plugin install @claude-community/tradeos

(Exact install name follows the catalog entry after approval.)


analyze skill

skills/analyze/SKILL.md teaches Claude when and how to call TradeOS MCP tools:

  • mcp_health, search_tickers, customize-agent, technical_analysis, bloomberg-oracle-terminal

  • Default workflows (single-symbol TA, macro/news, etc.)

Requires TradeOS MCP connected (plugin loads it via .mcp.json).


Other clients (Cursor, Codex, ChatGPT)

This repository is a Claude Code plugin. For other clients, see the TradeOS MCP product docs below.

Product docs: TradeOS MCP (GitBook)

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    D
    maintenance
    Connects MCP-compatible AI agents to GT Protocol trading accounts, enabling natural language control of automated trading bots, strategy backtesting, deal execution, and balance monitoring on Binance and Hyperliquid exchanges.
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to interact with Interactive Brokers through 48 tools for market data, orders, account management, and more, via the MCP protocol.
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables AI tools to execute trades and fetch market data across six crypto exchanges via natural language or API, with dual Telegram and MCP interfaces.
    2
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants in MCP clients to query real-time market data, inspect portfolio and Web3 wallet balances across brokers, place protected equity/ETF, crypto, forex, options, DeFi swap, and prediction market orders, and run backtests.
    MIT