Academic search and review generation MCP server
Project description
academic-mcp
一个用于学术任务的 MCP 服务,支持:
paper_search:跨多源检索论文(arXiv / Crossref / Semantic Scholar / CORE)generate_literature_review:基于检索结果自动生成综述草稿(可落盘到docs/)get_academic_config:查看当前 key/配置状态
1) 环境变量
复制 .env.example 为 .env,需要的 key 默认留空:
SEMANTIC_SCHOLAR_API_KEY=
CORE_API_KEY=
SCIENCEDIRECT_API_KEY=
SPRINGER_API_KEY=
IEEE_API_KEY=
SCOPUS_API_KEY=
说明:
- 本项目核心流程不强制依赖 key(arXiv/Crossref 可直接用)。
- 如需更高配额或付费源,再填对应 key。
2) uv 运行
在 academic-mcp/ 目录执行:
uv sync
uv run academic-mcp --transport stdio
HTTP 模式:
uv run academic-mcp --transport http --host 127.0.0.1 --port 8005
模块方式:
uv run python -m academic_mcp --transport stdio
3) 测试
uv run python tests/smoke_test.py
4) 发布
uv build
uv publish
可选 TestPyPI:
uv publish --index testpypi
5) OpenCode MCP 配置示例
{
"mcp": {
"academic-mcp": {
"type": "local",
"command": [
"uv",
"run",
"--directory",
"D:/OneDrive/WORK/Python/mcps/academic-mcp",
"academic-mcp"
],
"environment": {
"SEMANTIC_SCHOLAR_API_KEY": "",
"CORE_API_KEY": "",
"ACADEMIC_MCP_TRANSPORT": "stdio"
}
}
}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file academic_assistant_mcp-0.1.0.tar.gz.
File metadata
- Download URL: academic_assistant_mcp-0.1.0.tar.gz
- Upload date:
- Size: 51.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.8.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8cab887f456d12b335ae492ae34973eeb31b9753f0deea85b2fa6f7ebfa3d776
|
|
| MD5 |
e134328675ae63a280c3db7a65c80252
|
|
| BLAKE2b-256 |
ae3c325fec87348b468b187e43245fbdafeda2091c8357b0110070a1d1b7d463
|
File details
Details for the file academic_assistant_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: academic_assistant_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 8.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.8.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
56564e443aba4cfa40f6d9f3558ad9f506a5e4376a157e2e1246218e57d109d2
|
|
| MD5 |
2de96bc040cde33f85df5c6d0b73119a
|
|
| BLAKE2b-256 |
31a50185864160cd01beccb20ab72d73ba37ae3793cc12249409124e2552ed2b
|