Provides tools for retrieving detailed paper metadata by DOI, enabling AI agents to access academic paper details using Digital Object Identifiers.
Click on "Install 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., "@sci-bot-mcpWhat is the role of AI in drug discovery?"
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.
sci-bot-mcp
AI-powered research assistant MCP server for searching academic papers and answering research questions with DOI citations.
Basic Information
English name: sci-bot
Chinese name: 科研论文助手
Hosting type: Hosted deployment
Category: Research, Academic Search
Related MCP server: paper-fetch-mcp
MCP Service Configuration
{
"mcpServers": {
"sci-bot": {
"command": "python",
"args": ["server_stdio.py"],
"env": {
"DEEPSEEK_API_KEY": "your_deepseek_api_key",
"AI_BASE_URL": "https://api.deepseek.com",
"AI_MODEL": "deepseek-chat"
}
}
}
}Environment Variables
Variable | Required | Default | Description |
DEEPSEEK_API_KEY | Yes | - | DeepSeek API key used by |
AI_BASE_URL | No | OpenAI-compatible API endpoint. | |
AI_MODEL | No | deepseek-chat | Chat model name. |
MCP_TRANSPORT | No | auto |
|
PORT | No | 8000 | Hosted HTTP port supplied by the platform. |
MCP_PORT | No | 8000 | HTTP port fallback when |
HOST | No | 0.0.0.0 | HTTP bind host. |
Tools
search_papers
Search academic papers through CrossRef.
query(string): search query.limit(integer): number of results, default 8, max 20.
ask_research_question
Search papers and synthesize an answer with DOI references.
question(string): research question.num_references(integer): number of reference papers, default 8, max 15.
get_paper_details
Get detailed paper metadata by DOI.
doi(string): paper DOI.
Run Locally
Install dependencies:
pip install -r requirements.txtRun with stdio for local MCP clients:
python server_stdio.pyRun with SSE for direct HTTP deployment:
set MCP_TRANSPORT=sse
set PORT=8000
python server.pyHealth check endpoints:
//health
MCP endpoints:
/mcp/sse
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
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/lnkvv210-eng/sci-bot-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
