io.github.dev-flexorch/flexorch-mcp
FlexOrch
Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.
alive probed 2026-10-15
6tools
2.5ktokens in Claude Opus 5.5
2.6ktokens in Claude Code
1.3 %of a 200k context window
1.5ko200k_base estimate
2.4 sto initialize
6 msto list tools
- Run it
- uvx flexorch-mcp==0.1.2 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- flexorch 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Instructions
- 736 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/flexorch/flexorch-mcp
- Registry
- active, updated 2026-06-25 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| search_documents | 341 | 23 % |
| process_document | 318 | 21 % |
| export_dataset | 255 | 17 % |
| get_extraction_result | 217 | 15 % |
| build_dataset | 206 | 14 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.dev-flexorch/flexorch-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.