io.github.jgravelle/jdatamunch-mcp
jDataMunch MCP
Tabular data retrieval. Index CSV/Excel, query rows, aggregate. 99%+ savings vs raw file reads.
alive probed 2026-10-14
39tools
14ktokens in Claude Opus 5.5
15ktokens in Claude Code
7.0 %of a 200k context window
7.9ko200k_base estimate
2.1 sto initialize
8 msto list tools
- Run it
- uvx jdatamunch-mcp==1.31.13 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- jdatamunch-mcp 1.31.13
- Capabilities
- experimental, prompts, resources, tools
- Instructions
- 897 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/jgravelle/jdatamunch-mcp
- Registry
- active, updated 2026-08-31 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| finalize_handoff | 536 | 7 % |
| aggregate | 507 | 6 % |
| get_rows | 505 | 6 % |
| join_datasets | 425 | 5 % |
| index_local | 330 | 4 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.jgravelle/jdatamunch-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.