You're viewing a demo portfolio
Want to try it with your own data?
Add up to 10,000 DOIs or GitHub URLs at a time, bringing them and their related entities into the graph. Build portfolios and run queries across them.
Join the waitlistPRSM is built and maintained by one person. The platform works today, but opening it up will be slow and deliberate. If you want to help shape this infrastructure, or speed things up, let's talk.
com.stagenth/data-kit
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
biocontext
Not listed
glama
Not listed
mcp.so
Not listed
nerq
Not listed
pulsemcp
Not listed
smithery
Not listed
一步清洗脏数据:去重 / 去空白 / 删全空行列,产物落文件中转站并返清洗统计(1 credit/次)。
把数据文件转成另一种格式(csv/json/ndjson/parquet/xlsx),产物存文件中转站返下载 URL(1 credit/次)。 典型:把大 CSV 转 parquet 便于后续分析、或把 JSON 日志转 xlsx 给人看。失败自动退款。
查看数据文件结构:列名/类型/行数/每列非空数 + 前 N 行预览。免费(0 credit)。 支持 CSV/TSV/JSON/NDJSON/Parquet。取数(data_query)前先调它看清有哪些列、哪些是数值。
两份数据文件按共同列连接(如 订单表×客户表),返回实际数据行 JSON(1 credit/次)。 跨文件对齐是单文件 data_query 做不到的;DuckDB 引擎、锁死文件/网络访问。失败自动退款。
No matched repository in PRSM yet — maintainer attribution unavailable.
数据画像:每列类型/去重近似数/空值率 + 数值列 min/max/avg/std/分位数(1 credit/次)。 相当于 pandas df.describe()——AI 拿它一眼看清整份数据的分布与质量。失败自动退款。 返回 {ok, format, n_rows, n_cols, profile[]}。