research-radar-mcp (ScholarRadar MCP Server)
面向大学生的科研入门与文献追踪 MCP Server，为讯飞星辰（Astron）Agent 平台提供论文检索、相关性评分与中文导读卡片能力。逻辑移植自「科研雷达」后端，去除数据库 / Celery / Redis 依赖，可通过 uvx 独立运行。
工具（stdio）
| 工具 | 说明 | 依赖 |
|---|---|---|
search_papers |
按关键词检索近期 arXiv 论文 | 无状态（arXiv API） |
get_paper_detail |
获取单篇论文完整摘要与元数据 | 无状态（arXiv API） |
score_papers |
依据学生科研画像对论文批量打分 | 调用星火大模型 |
generate_digest |
生成中文导读卡片（创新点 / 方法要点 / 上手难度评级） | 调用星火大模型 |
环境变量
调用星火大模型的工具从环境变量读取凭据（由托管平台注入，不写入代码）：
| 变量 | 说明 | 默认 |
|---|---|---|
SPARK_API_KEY |
星辰 MaaS API Key（必填） |
— |
SPARK_BASE_URL |
OpenAI 兼容端点 | https://maas-api.cn-huabei-1.xf-yun.com/v2 |
SPARK_MODEL |
模型 ID | xsparkx2 |
运行
# 直接运行（已发布到 PyPI 后）
uvx research-radar-mcp
# 本地开发
uv sync
uv run research-radar-mcp
本地调试（MCP Inspector）
npx -y @cloudbase/mcp-inspector
# Transport = STDIO, Command = uvx, Args = research-radar-mcp
开发
uv sync
uv run pytest # 单元测试（mock arXiv / Spark，无需网络）
uv run ruff check .
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for research-radar-mcp 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| research_radar_mcp-0.2.1.tar.gz | 113.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| research_radar_mcp-0.2.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 126.9 kB
Release files / research_radar_mcp-0.2.1.tar.gz
| Download URL | research_radar_mcp-0.2.1.tar.gz |
|---|---|
| Size | 113.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
358df53cd5f99951ee7dd0e8118f6f950d03ccc95ccdbc3a7b3c202d42fc5b44
|
|
BLAKE2b-256 checksum How to use checksums |
aec6111ad5a7a96d0edd13769d089f93e69fd29bd58ae78b16d82aecb4399aca
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
Release files / research_radar_mcp-0.2.1-py3-none-any.whl
| Download URL | research_radar_mcp-0.2.1-py3-none-any.whl |
|---|---|
| Size | 13.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fabbbd794c05ebc2ac9f99deb76ad89cdb48c4b487cab607e720546251583723
|
|
BLAKE2b-256 checksum How to use checksums |
2c71ce0252e776f2ac3266a3c92806ac3515ee74deaac3c064939c5a8172f2d6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
Security for research-radar-mcp 0.2.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
