sci-bot-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | HTTP bind host. | 0.0.0.0 |
| PORT | No | Hosted HTTP port supplied by the platform. | 8000 |
| AI_MODEL | No | Chat model name. | deepseek-chat |
| MCP_PORT | No | HTTP port fallback when PORT is not set. | 8000 |
| AI_BASE_URL | No | OpenAI-compatible API endpoint. | https://api.deepseek.com |
| MCP_TRANSPORT | No | stdio, streamable-http, or sse. | auto |
| DEEPSEEK_API_KEY | Yes | DeepSeek API key used by ask_research_question. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_papersA | Search 200M+ academic papers using CrossRef API. Args: query: Search query (e.g. "CRISPR gene editing", "transformer attention mechanism") limit: Number of results to return (default 8, max 20) Returns: List of papers with title, authors, year, citation count, DOI, and abstract. |
| ask_research_questionA | Ask a research question and get an AI-generated answer with real paper citations. Searches academic papers and uses an LLM to synthesize an answer with proper citations [1][2][3]. Args: question: Your research question (e.g. "What are the latest CRISPR clinical applications?") num_references: Number of reference papers to use (default 8, max 15) Returns: A well-structured answer with inline citations and a reference list with DOIs. |
| get_paper_detailsA | Get detailed information about a specific paper by its DOI. Args: doi: The DOI of the paper (e.g. "10.1038/nature14539") Returns: Detailed paper info including full abstract, all authors, journal, and citation count. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: asking a research question, fetching paper details by DOI, and searching papers. There is no ambiguity or overlap.
All tools follow a consistent verb_noun pattern in snake_case: ask_research_question, get_paper_details, search_papers.
Three tools is on the lower end but still appropriate for a focused research assistant. Each tool serves a core function without unnecessary bloat.
Covers the main research workflow: search, details, and Q&A. Missing features like citation export or recommendations, but the surface is reasonably complete for its scope.