Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Daily News MCP Server Show me all news categories"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
claude mcp add daily-news \
-- uv --directory /path/to/daily-news run daily-news-mcpReplace
/path/to/daily-newswith your local project path.
cp -r openclaw-skill/daily-news ~/.openclaw/skills/6551-daily-newsRelated MCP server: cryptopolitan-mcp
Not sure if this MCP is safe? Paste the prompt below to your AI assistant — it will review the source code first, then install if safe:
Copy this prompt and send it to your AI assistant (replace
<project-path>with actual value):
Please review and install the daily-news-mcp MCP server for me. The project is at <project-path>.
Steps:
1. Review these files for security:
- src/daily_news_mcp/api_client.py — Confirm it only connects to ai.6551.io, no data sent elsewhere
- src/daily_news_mcp/config.py — Confirm no hardcoded secrets or leaks
- src/daily_news_mcp/tools.py — Confirm all tools only perform API queries, no file writes, command execution, or dangerous operations
- pyproject.toml — Confirm dependencies are only mcp, httpx, no suspicious packages
2. Tell me your conclusion: safe / risky / problematic, with specific reasons
3. If safe, run the install:
claude mcp add daily-news -- uv --directory <project-path> run daily-news-mcpOnce connected, just ask your AI assistant:
You say | It does |
"Show me all news categories" | List all available categories and subcategories |
"What's hot in DeFi today?" | Get hot news and tweets for the DeFi category |
"Get crypto market news" | Fetch trending news for the crypto market category |
"Show me AI-related news and tweets" | Get combined news + tweets for AI subcategory |
Tool | Description |
| Get all available news categories and subcategories |
| Get hot news and tweets by category/subcategory |
Variable | Required | Description |
| No | Override REST API URL (default: |
| No | Max results per query (default: 100) |
Also supports config.json in the project root (env vars take precedence):
{
"api_base_url": "https://ai.6551.io",
"max_rows": 100
}Endpoint | Method | Parameters | Description |
| GET | — | Get all news categories |
| GET |
| Get hot news + tweets |
[
{
"key": "crypto",
"name": "Crypto",
"name_zh": "加密货币",
"description": "...",
"subcategories": [
{
"key": "defi",
"name": "DeFi",
"name_zh": "去中心化金融",
"description": "..."
}
]
}
]{
"success": true,
"category": "crypto",
"subcategory": "defi",
"news": {
"success": true,
"count": 10,
"items": [
{
"id": 123,
"title": "...",
"source": "...",
"link": "https://...",
"score": 85,
"grade": "A",
"signal": "bullish",
"summary_zh": "...",
"summary_en": "...",
"coins": ["BTC", "ETH"],
"published_at": "2026-03-17T10:00:00Z"
}
]
},
"tweets": {
"success": true,
"count": 5,
"items": [
{
"author": "Vitalik Buterin",
"handle": "VitalikButerin",
"content": "...",
"url": "https://...",
"metrics": { "likes": 1000, "retweets": 200, "replies": 50 },
"posted_at": "2026-03-17T09:00:00Z",
"relevance": "high"
}
]
}
}In all configs below, replace
/path/to/daily-newswith your actual local project path.
Edit config (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"daily-news": {
"command": "uv",
"args": ["--directory", "/path/to/daily-news", "run", "daily-news-mcp"]
}
}
}~/.cursor/mcp.json or Settings > MCP Servers:
{
"mcpServers": {
"daily-news": {
"command": "uv",
"args": ["--directory", "/path/to/daily-news", "run", "daily-news-mcp"]
}
}
}~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"daily-news": {
"command": "uv",
"args": ["--directory", "/path/to/daily-news", "run", "daily-news-mcp"]
}
}
}Client | Config | Status |
Claude Code | CLI | Supported |
Claude Desktop | JSON config | Supported |
Cursor | JSON config | Supported |
Windsurf | JSON config | Supported |
Cherry Studio | GUI | Supported |
Zed | JSON config | Supported |
cd /path/to/daily-news
uv sync
uv run daily-news-mcp# MCP Inspector
npx @modelcontextprotocol/inspector uv --directory /path/to/daily-news run daily-news-mcp├── README.md # English
├── docs/
│ ├── README_ZH.md # 中文
│ ├── README_JA.md # 日本語
│ └── README_KO.md # 한국어
├── openclaw-skill/daily-news/ # OpenClaw Skill
├── pyproject.toml
├── config.json
└── src/daily_news_mcp/
├── server.py # Entry point
├── app.py # FastMCP instance
├── config.py # Config loader
├── api_client.py # HTTP client
└── tools.py # 2 toolsMIT
Get hot news and tweets by category.
Args: category: Category key (required). Use get_news_categories to list available keys. subcategory: Subcategory key (optional).
Returns: Combined news articles and tweets for the given category.
| Name | Required | Description | Default |
|---|---|---|---|
| category | Yes | ||
| subcategory | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose traits. It states it returns combined news and tweets, which is helpful, but does not mention side effects, auth, or limits. Adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a clear arg/return list. Could be slightly more streamlined, but no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 2-param tool with no output schema, the description covers purpose, parameters, return type, and references sibling for category enumeration. Lacks pagination or limit info but is sufficiently complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description explains category is a key from get_news_categories and subcategory is optional, adding meaning beyond the schema's type-only definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The verb 'Get' clearly indicates retrieval, and the resource is 'hot news and tweets by category'. It distinguishes from the sibling tool get_news_categories which lists categories.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description advises using get_news_categories to list available keys for the category parameter, providing explicit guidance on tool use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all available news categories and subcategories.
Returns a list of categories, each containing subcategories, for use with the get_hot_news tool.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It describes the return structure but does not disclose any behavioral traits like read-only nature, caching, or potential empty results. Adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, concise and front-loaded. No redundant or extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no parameters and no output schema, the description provides essential information: what it returns and how it relates to sibling tool. Missing details on return format, but adequate given simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Zero parameters; schema coverage is trivially 100%. Description adds no param info, but baseline for 0 params is 4. No need for additional semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Get all available news categories and subcategories' with a specific verb and resource. It distinguishes itself from sibling tool get_hot_news by noting its output is for use with that tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage context (for retrieving categories to use with get_hot_news) but does not explicitly state when not to use or provide alternatives. The link to get_hot_news provides clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_hot_newsget_news_categoriesScored across 2 tools
The two tools have clearly distinct purposes: one retrieves hot news by category, the other lists available categories. No ambiguity exists.
Both tools follow a consistent 'get_' prefix pattern, making it easy for an agent to infer their functionality.
With only 2 tools, the server feels minimal for a 'Daily News' purpose, missing typical operations like search or individual article retrieval, but it is not extreme.
The server covers only listing categories and fetching hot news, lacking search, filtering, or any write capabilities, leaving significant gaps for a news domain.
Real-time curated crypto news for AI agents with sentiment, recaps, and search.
Real-time financial news for AI agents: search by ticker and source, with sentiment and entities.
One call instead of crawling 29 news/finance/AI sources mid-task. 100 free queries/day.
Get access to real-time and historical news data including top headlines from global sources
