Opennews MCP

OpenNews MCP Server
84+ Real-time Data Sources · 6 Engine Categories · AI Ratings · Trading Signals

English | 中文 | 日本語 | 한국어

Quick Install

First, get your API Token at https://6551.io/mcp.

Claude Code

claude mcp add opennews \
  -e OPENNEWS_TOKEN=<your-token> \
  -- uv --directory /path/to/opennews-mcp run opennews-mcp

Replace /path/to/opennews-mcp with your local project path, and <your-token> with your API token.

OpenClaw

export OPENNEWS_TOKEN="<your-token>"
cp -r openclaw-skill/opennews ~/.openclaw/skills/

Let AI Review and Install

Not sure if this MCP is safe? Send the following prompt to your AI assistant to review the source code before installing:

Copy the prompt below and paste it to your AI assistant (replace <project-path> and <your-token> with actual values):

Please help me review and install the opennews-mcp MCP server. The project is at <project-path>.

Steps:
1. Review the security of the following files:
   - src/opennews_mcp/api_client.py — Confirm it only connects to ai.6551.io, no data sent elsewhere
   - src/opennews_mcp/config.py — Confirm token is only read from local config.json or env vars, not hardcoded or leaked
   - src/opennews_mcp/tools/*.py — Confirm all tools only do API queries, no file writes, command execution, or dangerous operations
   - pyproject.toml — Confirm dependencies are only mcp, httpx, websockets, no suspicious packages
2. Tell me your conclusion: Safe / Risky / Problematic, and the specific reasons
3. If safe, help me install (Token from https://6551.io/mcp):
   claude mcp add opennews -e OPENNEWS_TOKEN=<your-token> -- uv --directory <project-path> run opennews-mcp

Data Sources — 84+ Sources Across 6 Categories

All articles are AI-analyzed with impact score (0-100), trading signal (long/short/neutral), and bilingual summaries (EN/ZH).

What Can It Do?

After connecting, just tell your AI assistant:

Available Tools

For a comprehensive usage guide with detailed examples, see Knowledge Guide.

Configuration

Get API Token

Get your API Token at https://6551.io/mcp.

Set environment variable:

# macOS / Linux
export OPENNEWS_TOKEN="<your-token>"

# Windows PowerShell
$env:OPENNEWS_TOKEN = "<your-token>"

Also supports config.json in project root (env vars take precedence):

{
  "api_base_url": "https://ai.6551.io",
  "wss_url": "wss://ai.6551.io/open/news_wss",
  "api_token": "<your-token>",
  "max_rows": 100
}

WebSocket Real-time Subscriptions

Endpoint: wss://ai.6551.io/open/news_wss?token=YOUR_TOKEN

Subscribe to real-time crypto news updates.

Subscribe to News

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "news.subscribe",
  "params": {
    "engineTypes": {
      "news": ["Bloomberg", "CoinDesk"],
      "onchain": []
    },
    "coins": ["BTC", "ETH"],
    "hasCoin": true
  }
}

Response:

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "success": true,
    "filters": {
      "engineTypes": {...},
      "coins": [...],
      "hasCoin": true
    }
  }
}

Filter Parameters (all optional):

• engineTypes: Object mapping engine type to news type codes
  • Key: Engine type (e.g., "news", "onchain", "listing", "meme", "market", "prediction")
  • Value: Array of news type codes (e.g., ["Bloomberg", "CoinDesk"])
  • Empty array [] means all news types under that engine
  • Use list_news_types tool to get available codes
• coins: Array of coin symbols (e.g., ["BTC", "ETH"])
  • Filter news by specific coins
  • Empty array [] or omit to receive all coins
• hasCoin: Boolean, if true only receive news with coin tags

Unsubscribe

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "news.unsubscribe"
}

Server Push - News Update

When new news matches your filters, the server pushes:

{
  "jsonrpc": "2.0",
  "method": "news.update",
  "params": {
    "id": "unique-article-id",
    "text": "Article title or content",
    "newsType": "Bloomberg",
    "engineType": "news",
    "link": "https://...",
    "coins": [
      {
        "symbol": "BTC",
        "market_type": "spot",
        "match": "title"
      }
    ],
    "ts": 1708473600000
  }
}

Server Push - AI News Update

For news with AI analysis (if subscribed):

{
  "jsonrpc": "2.0",
  "method": "news.ai_update",
  "params": {
    "id": "unique-article-id",
    "text": "Article title",
    "newsType": "Bloomberg",
    "engineType": "news",
    "link": "https://...",
    "coins": [...],
    "aiRating": {
      "score": 85,
      "grade": "A",
      "signal": "long",
      "status": "done",
      "summary": "Chinese summary",
      "enSummary": "English summary"
    },
    "ts": 1708473600000
  }
}

Data Structure

Each article returns:

{
  "id": "unique-article-id",
  "text": "Title / Content",
  "newsType": "Bloomberg",
  "engineType": "news",
  "link": "https://...",
  "coins": [{ "symbol": "BTC", "market_type": "spot", "match": "title" }],
  "aiRating": {
    "score": 85,
    "grade": "A",
    "signal": "long",
    "status": "done",
    "summary": "Chinese summary",
    "enSummary": "English summary"
  },
  "ts": 1708473600000
}

{
  "mcpServers": {
    "opennews": {
      "command": "uv",
      "args": ["--directory", "/path/to/opennews-mcp", "run", "opennews-mcp"],
      "env": {
        "OPENNEWS_TOKEN": "<your-token>"
      }
    }
  }
}

{
  "mcpServers": {
    "opennews": {
      "command": "uv",
      "args": ["--directory", "/path/to/opennews-mcp", "run", "opennews-mcp"],
      "env": {
        "OPENNEWS_TOKEN": "<your-token>"
      }
    }
  }
}

{
  "mcpServers": {
    "opennews": {
      "command": "uv",
      "args": ["--directory", "/path/to/opennews-mcp", "run", "opennews-mcp"],
      "env": {
        "OPENNEWS_TOKEN": "<your-token>"
      }
    }
  }
}

{
  "mcpServers": {
    "opennews": {
      "command": "uv",
      "args": ["--directory", "/path/to/opennews-mcp", "run", "opennews-mcp"],
      "env": {
        "OPENNEWS_TOKEN": "<your-token>"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

mcpServers:
  - name: opennews
    command: uv
    args:
      - --directory
      - /path/to/opennews-mcp
      - run
      - opennews-mcp
    env:
      OPENNEWS_TOKEN: <your-token>

{
  "context_servers": {
    "opennews": {
      "command": {
        "path": "uv",
        "args": ["--directory", "/path/to/opennews-mcp", "run", "opennews-mcp"],
        "env": {
          "OPENNEWS_TOKEN": "<your-token>"
        }
      }
    }
  }
}

OPENNEWS_TOKEN=<your-token> \
  uv --directory /path/to/opennews-mcp run opennews-mcp

Compatibility

Related Projects

• twitter-mcp - Twitter/X data MCP server

Development

cd /path/to/opennews-mcp
uv sync
uv run opennews-mcp

# MCP Inspector test
npx @modelcontextprotocol/inspector uv --directory /path/to/opennews-mcp run opennews-mcp

Project Structure

├── README.md
├── openclaw-skill/opennews/   # OpenClaw Skill
├── knowledge/guide.md         # Embedded knowledge
├── pyproject.toml
├── config.json
└── src/opennews_mcp/
    ├── server.py              # Entry point
    ├── app.py                 # FastMCP instance
    ├── config.py              # Config loading
    ├── api_client.py          # HTTP + WebSocket
    └── tools/                 # Tools

License

MIT