MANNA

io.github.NSF-Simons-CosmicAI-Institute由 GitHub 账号 NSF-Simons-CosmicAI-Institute 发布v0.11.0更新于 Oct 30, 2026

MCP server for IVOA astronomical archives: NOIRLab Astro Data Lab, NRAO/ALMA, CADC, ESO, Gaia

概览

AI 生成的概览

为助手提供 IVOA 天文档案(Astro Data Lab、ALMA、CADC、ESO、Gaia、SDSS)访问的 MCP 服务器,支持 TAP/ADQL、图像与锥形搜索、注册表和 Sesame。

可以做什么
  • 解析天体名称并检索 IVOA 注册表中的档案
  • 对 TAP 服务执行 ADQL 查询,按位置搜索图像或星表源
  • 执行多步工作流:解析目标、选择档案并运行搜索或计数
  • 小结果直接内联返回,大型 TAP 结果转为异步任务并给出结果链接与 pyvo 片段
  • 读取各档案的整理说明,例如缺失字段与空间索引提示
适用场景
适合天文与天体物理场景:需要助手查询真实档案数据、针对特定服务编写 ADQL,或跨 IVOA 档案查找天体与图像,而不必手动构造每个请求。
运行要求
本地 Python 3.12 及以上运行时;用 uvx manna-mcp --stdio 运行或安装 manna-mcp 包。可选 MANNA_* 环境变量(MANNA_ARCHIVES、MANNA_ALLOWED_HOSTS、MANNA_INLINE_ROW_LIMIT、MANNA_LOG_LEVEL)或 .env 文件。需要访问档案服务的网络;首次启动会下载 astropy 与 pyvo。
安装前请注意
服务器会查询外部档案服务,请求内容会发送给这些第三方。大型结果不在服务器保留,只返回任务链接与代码片段,需由客户端自行获取。未设置 MANNA_ALLOWED_HOSTS 时允许访问任意公网主机,会扩大对外访问范围。首次启动较慢,可能超过客户端的短超时。

安装

在 SourceWeft 中

  1. 打开 控制台中的 MANNA,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

MANNA

[PyPI] [Documentation] [CI] [License: MIT]

MANNA (MCP Architecture for NOIRLab, NRAO, and additional Archives) is an MCP server that gives LLM clients such as Claude Code, Claude Desktop, and Jupyter AI access to astronomical archives through the standard IVOA interfaces: TAP/ADQL, SIA image search, cone search, the IVOA registry, and Sesame name resolution. It includes curated notes for NOIRLab Astro Data Lab, ALMA, CADC, ESO, Gaia, and SDSS, and can reach any archive listed in the IVOA registry.

Its tools fall into four groups:

  • Connections call the IVOA interfaces directly: resolve a target name, run an ADQL query, search for images or catalog sources by position, search the registry.
  • Workflow tools do a multi-step task in one call: resolve a target, pick an archive, run the search or count.
  • Result handling returns small results inline. A large TAP result becomes an async job, and the client receives a result URL and a pyvo snippet to fetch it. The server keeps nothing between requests.
  • Archive notes record each archive's quirks (missing columns, enum values, spatial-index hints) so the model sees them before writing ADQL. Every note has a check that re-verifies it.

Full documentation, including the reference for every tool, is at https://manna.readthedocs.io.

Installation

Python 3.12 or later. The PyPI distribution is manna-mcp; the import package and the command are both manna.

bash
uvx manna-mcp --stdio        # run without installing: MCP over stdiopip install manna-mcp        # or install it; `manna` then serves HTTP on :8000

The first launch downloads astropy and pyvo, which takes a while. Run uvx manna-mcp --stdio once in a terminal before adding it to a client with a short startup timeout.

The Docker image and the MCP Registry entry are described under Installation.

Connect a client

Claude Code:

bash
claude mcp add manna -- uvx manna-mcp --stdio

Claude Desktop, or any client with a JSON config:

json
{"mcpServers": {"manna": {"command": "uvx", "args": ["manna-mcp", "--stdio"]}}}

For a shared HTTP server or Jupyter AI, run manna and point the client at http://localhost:8000/mcp/.

Guides: Claude Code, Claude Desktop, Jupyter AI, a first query.

Configuration

All settings are optional and are read from MANNA_* environment variables or a .env file. The two most often changed:

  • MANNA_ARCHIVES=datalab,alma limits which archives have curated notes. Unset means every archive except nrao, which is inactive until named here.
  • MANNA_INLINE_ROW_LIMIT=2000 and MANNA_INLINE_BYTE_LIMIT=262144 raise the inline result caps from their small-model defaults to suit a large context window such as Claude's.

Every setting is listed in the configuration guide. Adding or removing an archive is covered in the archives guide.

Development

bash
git clone https://github.com/NSF-Simons-CosmicAI-Institute/mannacd mannauv syncuv run pytest --record-mode=none   # offline replay of recorded archive trafficuv run python -m manna             # server on http://localhost:8000

Feature branches are cut from dev and merged back by pull request. Tests, linting, recorded cassettes, the docs build, and releases are described under Contributing.

License

MIT. Developed by the NSF-Simons CosmicAI Institute.

来源:README.md,提交 eeff175

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

4
  1. v0.11.0最新Oct 9, 2026
  2. v0.10.0Sep 27, 2026
  3. v0.9.0Sep 16, 2026
  4. v0.7.2Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分