ChinaRxiv MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHINARXIV_EMAIL | Yes | Email sent in the X-API-Email header (required by upstream) | |
| CHINARXIV_TIMEOUT | No | Timeout in seconds for API requests (default: 30) | 30 |
| CHINARXIV_BASE_URL | No | Base URL of the ChinaRxiv API (default: https://chinarxiv.org) | https://chinarxiv.org |
| CHINARXIV_USER_AGENT | No | User-Agent header value (default: mcp-chinarxiv/0.1) | mcp-chinarxiv/0.1 |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_papersC | Search and filter papers in the unified ChinaRxiv/RussiaRxiv corpus. |
| get_paper_detailB | Get ChinaRxiv paper metadata/details by paper ID. |
| get_paper_full_textA | Get full text for a ChinaRxiv paper by paper ID. Returns markdown when the API provides it. |
| get_paper_figuresC | Get figure metadata or extracted figures for a ChinaRxiv paper. |
| download_paper_pdfC | Download an English paper PDF, following the upstream redirect and returning file metadata. |
| list_subjectsC | List ChinaRxiv subjects. |
| list_publicationsC | List journals/publications with translated papers. |
| get_api_statsC | Get ChinaRxiv API statistics. |
| list_bulk_exportsA | List available ChinaRxiv bulk exports. The upstream API documents this as rate limited. |
| health_checkC | Check ChinaRxiv API health. |
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 10 tools
Each tool targets a distinct resource or action: downloading PDFs, retrieving metadata, full text, figures, searching, listing various entities, and health/stats. No two tools have overlapping purposes.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., download_paper_pdf, get_paper_detail, list_subjects). Minor exception like health_check still fits the pattern.
With 10 tools, the server is well-scoped for a preprint repository access tool. Each tool serves a clear purpose without unnecessary duplication.
Core operations for finding and retrieving papers are covered: search, metadata, full text, figures, PDF download. Minor gaps like browsing by author or getting recent papers are missing but search can partially compensate.