generate_daily_summary

Generate a daily summary of AI research activity by aggregating papers, GitHub repositories, and Hugging Face models to track research progress.

Instructions

Generate a comprehensive daily summary of AI research activity

Input Schema

TableJSON Schema

Name	Required	Description
`include_papers`	No	Include papers section
`include_repos`	No	Include GitHub repos section
`include_models`	No	Include Hugging Face models section

Implementation Reference

src/ai_research_mcp/server.py:508-534 (handler)

Core handler function that implements the generate_daily_summary tool logic by fetching data from arXiv, HuggingFace, GitHub and formatting a markdown daily summary.

async def _generate_daily_summary(
    self,
    include_papers: bool = True,
    include_repos: bool = True,
    include_models: bool = True,
) -> str:
    """Generate daily summary."""
    sections = []
    sections.append(f"# AI Research Daily Summary\n*Generated: {datetime.now().strftime('%Y-%m-%d %H:%M')}*\n")
    
    if include_papers:
        # Get papers from multiple sources
        hf_papers = await asyncio.to_thread(self.huggingface.get_daily_papers, days=1)
        arxiv_papers = await asyncio.to_thread(self.arxiv.get_latest_papers, days=1, max_results=20)
        
        all_papers = hf_papers + arxiv_papers
        sections.append(f"## 📄 Today's Featured Papers ({len(all_papers)})\n\n{self._format_papers(all_papers[:15])}")
    
    if include_repos:
        repos = await asyncio.to_thread(self.github.get_trending_repositories, period="daily")
        sections.append(f"## 🔥 Trending Repositories ({len(repos)})\n\n{self._format_repos(repos[:10])}")
    
    if include_models:
        models = await asyncio.to_thread(self.huggingface.get_llm_models, limit=15)
        sections.append(f"## 🤖 Popular Models ({len(models)})\n\n{self._format_models(models[:10])}")
    
    return "\n\n".join(sections)

src/ai_research_mcp/server.py:212-235 (registration)

Tool registration in list_tools() handler, including name, description, and input schema.

Tool(
    name="generate_daily_summary",
    description="Generate a comprehensive daily summary of AI research activity",
    inputSchema={
        "type": "object",
        "properties": {
            "include_papers": {
                "type": "boolean",
                "description": "Include papers section",
                "default": True,
            },
            "include_repos": {
                "type": "boolean",
                "description": "Include GitHub repos section",
                "default": True,
            },
            "include_models": {
                "type": "boolean",
                "description": "Include Hugging Face models section",
                "default": True,
            },
        },
    },
),

src/ai_research_mcp/server.py:215-234 (schema)

Input schema definition for the generate_daily_summary tool, specifying optional boolean flags for sections.

inputSchema={
    "type": "object",
    "properties": {
        "include_papers": {
            "type": "boolean",
            "description": "Include papers section",
            "default": True,
        },
        "include_repos": {
            "type": "boolean",
            "description": "Include GitHub repos section",
            "default": True,
        },
        "include_models": {
            "type": "boolean",
            "description": "Include Hugging Face models section",
            "default": True,
        },
    },
},

src/ai_research_mcp/server.py:278-279 (registration)
Dispatch logic in call_tool() handler that routes calls to the _generate_daily_summary method.
```
elif name == "generate_daily_summary":
    result = await self._generate_daily_summary(**arguments)
```

AI Research MCP Server