Sdcreader
What it does
Read published Semantic Data Charter models: catalog search, record structure, codes, pinned schema.
- Connects 在你的电脑上运行
- Account or key No key needed
- Category 搜索与 AI 记忆
安装
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月13日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
打开电脑版 Claude 应用的设置文件
SettingsDeveloperEdit Config
粘贴这些设置并保存文件
{ "mcpServers": { "sdcreader": { "command": "uvx", "args": [ "sdcreader" ] } } }退出 Claude 再重新打开
试一试
用 Sdcreader 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Sdcreader,或回答中出现 Sdcreader 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Sdcreader
Sdcreader 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
你可以改用这些方式
A · 使用能连接 Sdcreader 的应用
- 需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
- 需要先在电脑上安装 Python (uv)(只需一次)
- 需要先在电脑上安装 Python (uv)(只需一次)
- 需要先在电脑上安装 Python (uv)(只需一次)
B · 搜索与 AI 记忆 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
- Context7✓ ChatGPT
- AIHOT✓ ChatGPT
- Sui Knowledge Base (kapa.ai)✓ ChatGPT
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --scope user sdcreader -- uvx sdcreader在 Claude Code 中输入 /mcp
应能看到 Sdcreader 在列表中并显示已连接
试一试
用 Sdcreader 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Sdcreader,或回答中出现 Sdcreader 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 Sdcreader 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Sdcreader,或回答中出现 Sdcreader 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 Sdcreader 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Sdcreader,或回答中出现 Sdcreader 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
开发者专用:终端命令和 JSON 设置
安装在电脑上
Claude Code
claude mcp add --scope user sdcreader -- uvx sdcreaderClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"sdcreader": {
"command": "uvx",
"args": [
"sdcreader"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"sdcreader": {
"command": "uvx",
"args": [
"sdcreader"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"sdcreader": {
"type": "stdio",
"command": "uvx",
"args": [
"sdcreader"
]
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月13日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 SemanticDataCharter 验证,该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于3天前
- ✓ 通过
有许可证
使用 Apache-2.0
- – 不适用
端点有响应
它在你的电脑上运行,没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行,改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行;我们只能读取互联网端点的工具列表
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“搜索与 AI 记忆”中的其他服务器比较i
- 星标数多于此分类中其他 6046 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 6046 个服务器的 67% 更新
- 基础检查结果等于或优于此分类中其他 6046 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Sdcreader 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
它还在维护吗?
GitHub 仓库最后更新于3天前,最新版本(4.4.1)于18天前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
有什么可以替代它?
同一分类中有:Context7, Codebase Memory, Ruflo
同类别的其他选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
sdcreader
Read a published Semantic Data Charter model's package for projection into other standards.
A projection describes a model's governed data records in another standard's terms: CDIF, DCAT-US 3.0, DCAT-AP 3.0.1, HealthDCAT-AP, and whatever comes next. What every projection describes is the same evidence, the model's package, and reads it into the same shape. sdcreader is that evidence and that shape, once, with nothing about any projection in it. The four projection writers (sdc_cdif, sdc_dcat3_us, sdc_dcat3_ap, sdc_healthdcat_ap) carried it as identical copies until this package.
pip install sdcreader # the reader, with HTTP for fetching from the public catalog (since 4.1.0 no extra is needed)
from sdcreader import fetch_package, load_package, read_model
pkg = load_package("samples/nhanes-participant") # a package on disk pkg = fetch_package("xy8upneajsb8vdcmnve01g6g", save_to="pkg/") # or from SDCStudio's public catalog, no account model = read_model(pkg)
pkg.schema_url_pinned # https://sdcstudio.axius-sdc.com/dmlib/dm-xy8u...xsd?sha256=0df4... the exact bytes the records are validated against model.title, model.leaves # 'NHANES Participant', 153 leaves in document order, each with its path of clusters model.codes[ct_id] # the enumerated values of a component with the IRI, definition and code the schema annotates them with model.dc("publisher") # what the modeler wrote, None where SDCStudio's default sits
What a package is
SDCStudio generates a package for every published model and serves it publicly for models in public projects:
GET /api/v1/catalog/dm/ / | the catalog record: title, description, project, the artifact list (catalog.json) |
GET /api/v1/catalog/dm/ / / | a storage pointer, {"download_url": ..., "filename": ..., "storage": "gcs"}, for jsonld, xsd and the rest; the reader follows it |
dm- .jsonld | the model and its components: type, label, description, cardinality, constraints (enumerations, units, ranges, patterns), semantic links (dcterms:identifier the library slot, dcterms:source, dcterms:publisher, skos:exactMatch, rdfs:seeAlso, prov:wasRevisionOf), contains |
GET /dmlib/dm- .xsd | the schema bytes: the Dublin Core header for the model, and for each enumerated value its definition and the code it is defined by (dm- .xsd) |
GET /dmlib/dm- .versions.json | every published version of the schema by SHA-256, with the current one (versions.json) |
A package directory holds those four files. The reader refuses a directory without the JSON-LD and the schema, a JSON-LD whose identifier is not the directory's model, and a schema whose bytes are not the published current version: a projection cites the schema by URL and SHA-256, so the bytes have to be the ones that URL serves.
Two gaps in the package are on SDCStudio's issue tracker: the JSON-LD metadata drops fields the schema header carries (#748), and the header omits dc:source (#749). The reader takes the model's Dublin Core from the header, which is complete.
What the reader gives
- `ModelPackage`: the four files, the SHA-256, the schema URL and its pinned form (
?sha256=), the public catalog URL, andcheck(). - `Model`:
title,description,root(the governed record's cluster),componentsby identifier,leavesin document order (each aLeafwith itscomponent, itspathof clusters and aslugof that path, unique in the record),codes(the enumerated values per component asCode: value, IRI, definition, the code it is defined by),metadata(the JSON-LD's) andheader(the schema's Dublin Core). - `Model.dc(name)`: what the modeler wrote, the header first and the JSON-LD second, with SDCStudio's field defaults as unset: "Universal" for coverage, "None" for relation, "SDC Data Model (DM)" for type, blanks. A projection never publishes a default as a fact.
contributors,subjects(the semicolon list),rights_urlandrights_statementderive from it. - `Component`:
sdc_type,label,description,data_type,constraints,linksby predicate (link(p)for the first),contains,iri. - Constants: the leaf, numeric and quantified types; the predicate IRIs
IDENTIFIER,SOURCE,PUBLISHER,EXACT,CLOSE,SEE_ALSO,HAS_UNIT;DC_DEFAULTS.
Reading a record (4.3.0)
read_record(source, model) reads a Governed Data Record, the XML instance, and joins each value to the component that defines it. source is the record's bytes, its text or a path; a record of another model is refused (RecordError), as is anything that is not an sdc4:dm- record.
- `Record`:
attributes(instance_id,instance_version,creation_timestamp,current-state, ...),valuesin document order, andexceptional, the values that carry an Exceptional Value. - `RecordValue`: the
component, itspathof clusters (root first),instancesparallel to the path (which occurrence each cluster is among the same cluster's repeats under the same parent;instance_keypairs them with the clusters' identifiers, one key per cluster instance), anoccurrenceindex for a component repeated within its cluster instance, itsposition, itselementsas the record holds them (a quantity's units nested:{"xdquantity-value": "1", "xdquantity-units": {"label": "Trade Units", "xdstring-value": "EA"}}), and itscontext(act,vtb,vte,tr,modified,latitude,longitude). - `ExceptionalValue`: the ISO 21090 null flavor (
code,name) and itsorigin:sourcewhen it stands in place of the value,recoverywhen sdcvalidator's recovery inserted it beside a value that failed its constraint. Forrecovery,RecordValue.rejectedis that value, kept so a person can see it.
Cluster members sit inside adapter elements that are not components of the model; the reader passes through them. It does not type, validate or interpret values: that is the caller's work (a mapper, an exporter, a checker).
MCP server
sdcreader is also an MCP server, registered as io.github.SemanticDataCharter/sdcreader, so an assistant can read a published model the way sdcvalidator, sdcgovernance and sdcreceipt let it validate, govern and settle a record. stdio, no SDK, no account, read-only.
uvx sdcreader # or: sdcreader-mcp, or python -m sdcreader.mcp_server
uvx sdcreader --host https://your-sdcstudio.example # a sovereign SDCStudio's public catalog
| Tool | Does |
|---|---|
find_models | search the public catalog by text, or list a public project's models by name |
describe_model | one model: title, project, root record, leaf and component counts by type, Dublin Core with SDCStudio's defaults as null, the schema URL pinned to its SHA-256 |
list_leaves | the leaves in document order with path, type, constraints, code count and identity links, paged |
list_codes | one component's enumerated values with IRI, definition and code system |
check_package | the reader's integrity check on a package directory |
read_record | a Governed Data Record on disk read against its model: attributes, then each value with its component, path, elements, context and Exceptional Value, paged; the model is the one the record names unless a source is given |
Each model tool takes a ct_id (fetched from the host the server was started with) or a package directory on disk. No tool takes a URL: the host is fixed at start, so a caller cannot point the server elsewhere. Every tool calls the same functions as the library; the two interfaces describe one model the same way.
Tests
pip install -e ".[dev]"
python -m pytest tests -q # includes one fetch against production python -m pytest tests -q -m "not network" # offline, as CI runs it
The fixture is the NHANES Participant package of the FAIR Data Demo, the record every projection is proven on.
Versioning
The leading 4 is the SDC4 reference model, as with every Semantic Data Charter package. An addition to what the reader exposes is a minor version, a fix a patch; the major changes only when the reference model does.
License
Apache-2.0 (see LICENSE, NOTICE).