io.github.haiiibin/data-profiler-mcp
data-profiler
Profiles CSV/Parquet/Excel/JSON files: schema, stats, quality flags and dtype tips for LLM agents.
alive probed 2026-10-14
7tools
2.6ktokens in Claude Opus 5.5
2.7ktokens in Claude Code
1.3 %of a 200k context window
1.5ko200k_base estimate
5.6 sto initialize
6 msto list tools
- Run it
- uvx data-profiler-mcp==0.4.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- data-profiler
- Capabilities
- prompts, resources, tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/haiiibin/data-profiler-mcp
- Registry
- active, updated 2026-10-09 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| profile_dataset | 291 | 19 % |
| correlation_matrix | 283 | 18 % |
| column_stats | 227 | 15 % |
| detect_quality_issues | 222 | 14 % |
| compare_datasets | 184 | 12 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.haiiibin/data-profiler-mcp)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.