Skip to main content
Glama
PlayAINetwork

ChainGPT AI News MCP Server

ChainGPT AI News MCP Server

A Model Context Protocol (MCP) server that provides access to AI-related crypto and Web3 news through the ChainGPT AI News API.

Features

  • Smart Filtering: Filter news by categories, blockchains, tokens, and keywords

  • Date Range Support: Fetch news from specific time periods

  • Category Mapping: Supports 20+ categories including DeFi, NFTs, Gaming, DAOs, and more

  • Blockchain Coverage: Covers 40+ blockchains including Ethereum, Bitcoin, Solana, Polygon, and others

  • Token Tracking: Track news for 30+ major cryptocurrencies

  • Pagination: Handle large result sets with limit/offset controls

  • Real-time Data: Access to the latest crypto and Web3 news

Related MCP server: test-newsapi-mcp

Integration with MCP Clients

Claude Desktop

Add to your Claude Desktop configuration:


{
  "mcpServers": {
    "chaingpt-mcp": {
      "command": "npx",
      "args": ["chaingpt-mcp-server"],
      "env": {
        "CHAINGPT_API_KEY": ""
      }
    }
  }
}

Installation

Prerequisites

  • Node.js 18+

  • npm or yarn

  • ChainGPT API key

Setup

  1. Clone the repository:

git clone https://github.com/PlayAINetwork/Chaingpt-mcp.git
cd <folder-name>
  1. Install dependencies:

pnpm install
  1. Set up environment variables:

export CHAINGPT_API_KEY=your_api_key_here

Or create a .env file:

CHAINGPT_API_KEY=your_api_key_here
  1. Run the server:

node index.js

Getting a ChainGPT API Key

  1. Visit ChainGPT's website

  2. Sign up for an account

  3. Navigate to the API section

  4. Generate your API key

  5. Add it to your environment variables

Usage

Basic Usage

The server provides a single tool called getAINews with the following parameters:

{
  categories: ["defi", "nft"],           // Optional: Filter by categories
  blockchains: ["ethereum", "solana"],  // Optional: Filter by blockchains
  tokens: ["bitcoin", "ethereum"],      // Optional: Filter by tokens
  searchQuery: "AI development",        // Optional: Keyword search
  fetchAfter: "2024-01-01T00:00:00Z",  // Optional: Date filter
  limit: 10,                           // Optional: Number of results (default: 10)
  offset: 0                            // Optional: Pagination offset (default: 0)
}

Example Queries

Get latest DeFi news:

{
  "categories": ["defi"],
  "limit": 5
}

Get Ethereum-related news from the last week:

{
  "blockchains": ["ethereum"],
  "fetchAfter": "2024-01-01T00:00:00Z",
  "limit": 20
}

Search for AI-related crypto news:

{
  "searchQuery": "artificial intelligence",
  "categories": ["cryptocurrency", "web3"],
  "limit": 15
}

Response Format

The server returns structured JSON responses:

{
  "status": "success",
  "metadata": {
    "totalResults": 10,
    "limit": 10,
    "offset": 0,
    "appliedFilters": {
      "categories": ["defi"],
      "blockchains": [],
      "tokens": [],
      "searchQuery": null,
      "fetchAfter": null,
      "mappedIds": {
        "categoryIds": [5],
        "subCategoryIds": [],
        "tokenIds": []
      }
    },
    "timestamp": "2024-01-15T10:30:00Z"
  },
  "data": [
    {
      "id": "article_id",
      "title": "Latest DeFi Development",
      "description": "Article description...",
      "url": "https://example.com/article",
      "publishedAt": "2024-01-15T09:00:00Z",
      "source": "CryptoNews",
      "category": "DeFi",
      "blockchain": "Ethereum"
    }
  ]
}

Error Handling

The server provides detailed error responses:

{
  "status": "error",
  "message": "ChainGPT API key not found. Please set the CHAINGPT_API_KEY environment variable.",
  "suggestion": "Add CHAINGPT_API_KEY=your_api_key to your environment variables"
}

Common error scenarios:

  • Missing API key

  • Invalid date format

  • API rate limiting

  • Network connectivity issues

Development

Project Structure

chaingpt-ainews-mcp/
├── index.js              # Main server file
├── package.json          # Dependencies and scripts
├── README.md            # This file
├── .env.example         # Environment variables template
└── .gitignore          # Git ignore rules

Dependencies

  • @modelcontextprotocol/sdk - MCP SDK

  • @chaingpt/ainews - ChainGPT AI News API client

  • zod - Schema validation

Contributing

  1. Fork the repository

  2. Create a feature branch: git checkout -b feature/your-feature

  3. Make your changes

  4. Add tests if applicable

  5. Commit your changes: git commit -m 'Add some feature'

  6. Push to the branch: git push origin feature/your-feature

  7. Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

Available Tools

1 tool
getAINewsA

Fetch the latest AI-related crypto and Web3 news with optional filtering by categories, blockchains, tokens, keywords, and date range

ParametersJSON Schema
NameRequiredDescriptionDefault
categoriesNoCategories to filter by (e.g., ['defi', 'nft', 'gaming', 'dao', 'metaverse'])
blockchainsNoBlockchains/networks to filter by (e.g., ['ethereum', 'bitcoin', 'solana', 'polygon'])
tokensNoTokens/cryptocurrencies to filter by (e.g., ['bitcoin', 'ethereum', 'usdt', 'bnb'])
searchQueryNoKeyword or phrase to search for in news titles and descriptions
fetchAfterNoOnly return news published after this date (ISO 8601 format, e.g., '2024-01-01T00:00:00Z')
limitNoNumber of news articles to return (default: 10)
offsetNoNumber of items to skip for pagination (default: 0)

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are present, so the description carries full burden. It accurately implies a read-only operation but does not disclose any behavioral details beyond basic fetching, such as data source, rate limits, or error handling.

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?

Single sentence that front-loads the action and efficiently enumerates filters. No wasted words; structure is clear and scannable.

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

Completeness4/5

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

Given 7 optional parameters and no output schema, the description covers the main functionality and filter options. It omits output format but this is acceptable without an output schema. Could mention return type briefly.

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?

Input schema coverage is 100%, so the schema already documents parameters. The description merely summarizes filter options without adding new meaning or constraints beyond what the schema provides.

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

Purpose5/5

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

The description clearly states 'Fetch the latest AI-related crypto and Web3 news with optional filtering...' using a specific verb and resource. It distinguishes the tool's scope even without siblings.

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

Usage Guidelines3/5

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

The description lists what the tool does but provides no guidance on when to use it versus alternatives or any prerequisites. Without siblings, this is less critical, but still lacking explicit context.

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. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.1
    • First observedgetAINews

TDQS

A3.8/5.0
Disambiguation5/5

Only one tool exists, so there is no ambiguity between tools. The agent can only select this single tool, making misselection impossible.

Naming Consistency5/5

With a single tool, naming conventions are trivially consistent. The name 'getAINews' follows camelCase and clearly describes the action.

Tool Count2/5

A single tool is far below the typical 3-15 range for a news server. While the scope is narrow, more tools (e.g., categories, search, trending) would likely be expected.

Completeness3/5

The tool provides fetching news with filters, which covers the primary use case. However, missing operations like retrieving specific articles, managing sources, or subscribing leave notable gaps.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Provides AI agents access to news aggregation from 80,000+ sources via the NewsAPI. Supports both authenticated access with API keys and pay-per-use via HTTP 402 protocol with blockchain payment verification.
    -
  • F
    license
    A
    quality
    D
    maintenance
    Connects LLMs to NewsData.io to search for latest news, cryptocurrency trends, and financial market data with advanced filtering options. It enables users to access real-time headlines, historical archives, and news sources directly through natural language.
    5
    -
  • A
    license
    B
    quality
    F
    maintenance
    Real-time cryptocurrency news, analysis, and price predictions for AI agents. 5 tools to search 50,000+ articles across 12 categories, filter by 120+ asset tickers, and access content with built-in attribution. Free with attribution. SSE and Streamable HTTP transport.
    4
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/PlayAINetwork/Chaingpt-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server