This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Affected surfaces
Summary
AI summaryFixed Claude Code MCP trust approval by ensuring the one-time registration command is printed and documented.
Full changelog
What's New
Fixed
- Claude Code MCP trust approval —
install.shnow prints the one-time trust command in all post-install output variants.CLAUDE.mdalso includes it prominently. Without this step, Claude Code silently ignores.mcp.jsondue to its project-scope security approval requirement.
The fix
After installing, Claude Code users need to run once:
claude mcp add --transport sse --scope project flaiwheel http://localhost:8081/sse
This registers Flaiwheel as a trusted project-scoped MCP server. After that, .mcp.json loads automatically on every session. Verify with /mcp inside Claude Code — flaiwheel should appear with 27 tools listed.
Upgrade
curl -sSL https://raw.githubusercontent.com/dl4rce/flaiwheel/main/scripts/install.sh | bash
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About dl4rce/flaiwheel
Self-hosted memory and governance layer for AI coding agents. 28 MCP tools with structured knowledge capture, hybrid search (semantic + BM25 + cross-encoder reranking), behavioral documentation nudges, cold-start codebase analyzer, and git-native storage. Single Docker container, zero cloud dependencies.
Related context
Beta — feedback welcome: [email protected]