Skip to content

n24q02m/mnemo-mcp

v1.24.1 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

Published 1mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents ai-coding ai-memory claude claude-code cursor
+8 more
docker hybrid-search mcp mcp-server model-context-protocol python rclone sqlite

Affected surfaces

auth deps

Summary

AI summary

Removed the _share_cloud_keys_to_peers credential option for per‑server isolation.

Full changelog

v1.24.1 (2026-04-28)

This release is published under the MIT License.

Bug Fixes

  • Clarify default-local relay URL in setup docs (no n24q02m subdomain) (#521, c8dc075)

  • Pass MCP_TRANSPORT=stdio in plugin.json + uv run --no-sync hooks (#523, a247bfc)

  • Pass MCP_TRANSPORT=stdio in plugin.json + uv run --no-sync hooks (#522, c1e02a1)

  • credentials: Rip _share_cloud_keys_to_peers — per-server isolation (#523, a247bfc)

  • deps: Bump n24q02m-mcp-core to 1.10.0 — Transparent Bridge waves 1-3 (#525, 2fdce51)

  • lint: Ruff format pass (#523, a247bfc)

Detailed Changes: v1.24.0...v1.24.1

Breaking Changes

  • Removed _share_cloud_keys_to_peers from the credentials configuration (per‑server isolation)
View diff on GitHub

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

Share on X Share on Bluesky

Track n24q02m/mnemo-mcp

Get notified when new releases ship.

Sign up free

About n24q02m/mnemo-mcp

Persistent AI memory with SQLite hybrid search (FTS5 + semantic). Built-in Qwen3 embedding, rclone sync across machines. Zero config, no cloud, no limits.

All releases →

Related context

Beta — feedback welcome: [email protected]