AI Research MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CACHE_DIR | No | Cache directory (optional, defaults to .cache) | .cache |
| GITHUB_TOKEN | No | GitHub Personal Access Token to increase API rate limits from 60 req/h to 5000 req/h | |
| CACHE_EXPIRY_ARXIV | No | Cache expiry time for arXiv search results in seconds (2 hours) | 7200 |
| CACHE_EXPIRY_GITHUB | No | Cache expiry time for GitHub API results in seconds (1 hour) | 3600 |
| CACHE_EXPIRY_SUMMARY | No | Cache expiry time for daily/weekly summaries in seconds (24 hours) | 86400 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_latest_papersC | Search for latest AI/ML research papers from multiple sources (arXiv, Papers with Code, Hugging Face) |
| search_github_reposC | Search for trending AI/ML GitHub repositories |
| get_daily_papersB | Get today's featured AI papers from Hugging Face |
| get_trending_reposC | Get trending AI/ML repositories on GitHub |
| get_trending_modelsB | Get trending AI models from Hugging Face |
| search_by_areaB | Search papers and repos by research area (llm, vision, robotics, bioinfo, etc.) |
| generate_daily_summaryC | Generate a comprehensive daily summary of AI research activity |
| generate_weekly_summaryC | Generate a comprehensive weekly summary of AI research activity |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Daily AI Research Summary | Today's AI research summary including papers, repos, and models |
| Weekly AI Research Summary | This week's AI research summary |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/nanyang12138/AI-Research-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server