Skip to content

Releases: nicotem/qualcoder_mcp

v0.8.0-alpha

v0.8.0-alpha Pre-release
Pre-release

Choose a tag to compare

@nicotem nicotem released this 26 Jul 09:29

Connect QualCoder to Claude for AI-assisted qualitative data analysis — explore your coded data conversationally, code with a human-in-the-loop approval gate, and now: let the AI propose new codes you review before they exist.
This is an alpha. It works and it's been tested hard, but it's early — please work on copies of your projects, never originals.

New in this release

Inductive / open coding — the AI can propose brand-new codes from your data, with supporting evidence. You review, rename, recolour, merge or reject every proposal; nothing exists until you approve it, and creation is all-or-nothing with a backup first.
One-word span control — every coding suggestion carries precomputed shorter/longer span alternatives (sentence ↔ full speaker turn), so "longer on #3" fixes a quote instantly. Born directly from early tester feedback.
Report exports — codebook, coded-segments report, and frequency/matrix CSVs, with counting rules matched against QualCoder's own source so the numbers agree with your Reports screen (any deliberate divergence is stated in the output). Optional sanitize_formulas flag for spreadsheet safety.
Cases, attributes & annotations — create cases, define and set attributes (with correct numeric semantics), write annotations; plus merge_category and backup retention (prune_backups).
Editable suggestions — adjust a pending suggestion's span or code before approving (edit_suggestion).
Works in Claude Desktop, Claude Code, or any MCP client (new docs section).
Tool surface: 48 → 67. Test suite: 1130 automated tests, cross-platform CI (macOS/Linux/Windows, Python 3.10 & 3.13). Every feature implemented against QualCoder 3.8.2 source ground truth and gated through independent QA and security review. This release also fixes two subtle v0.7 bugs the ground-truth research exposed (numeric attribute queries matching unset values; case-link duplicate detection).

Safety

Read-only by default. Every write is preceded by an automatic backup, verified against QualCoder's format, and refused while QualCoder has the project open. Destructive operations preview first and take a safety backup.

Requires

Python 3.10+, a Claude client (Desktop or Code), QualCoder 3.8.x with at least one project. macOS, Linux, or Windows.

Support

Bugs, questions, and feature ideas via GitHub Issues — see SUPPORT.md. Early adopters shape the roadmap — this release's span controls and multi-code guidance came straight from the first tester.
Full changelog: CHANGELOG.md. MIT licensed, no warranty.

v0.7.0-alpha

v0.7.0-alpha Pre-release
Pre-release

Choose a tag to compare

@nicotem nicotem released this 18 Jul 10:40

Connect QualCoder to Claude Desktop for AI-assisted qualitative data analysis — explore your coded data conversationally, and code, edit your codebook, and write memos with a human-in-the-loop approval gate.
This is an alpha. It works and it's been tested hard, but it's early — please work on copies of your projects, never originals.

New in this release

Memo writing — annotate codes, categories, files, codings, and cases; keep a research journal.
Full codebook editing — create, rename, recolour, merge, move, and delete codes and categories, conversationally. Destructive operations (merge, delete) preview the change and take a safety backup first, and match QualCoder's own behaviour (verified against its source).
Building on v0.6.0-alpha's working AI-coding loop, undo/restore tooling, REFI-QDA export, and concurrency safety.

Safety

Read-only by default. Every write is preceded by an automatic backup, verified against QualCoder's format, and refused while QualCoder has the project open (it asks you to close it first) so the two can't corrupt each other. 879 automated tests; reviewed for security; behaviour checked against QualCoder 3.8.2 source. CI green on macOS, Linux, and Windows.

Requires

Python 3.10+, Claude Desktop, QualCoder 3.8.x with at least one project. macOS, Linux, or Windows.

Support

Bug reports, questions, and feature ideas all go through GitHub Issues — see SUPPORT.md. Early adopters shape the roadmap; feature ideas are as welcome as bug reports.
Full changelog: CHANGELOG.md. MIT licensed, no warranty.