This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+8 more
Summary
AI summaryAdd batch extract with per‑domain rate limiting.
Full changelog
v2.14.0 (2026-03-17)
This release is published under the MIT License.
Bug Fixes
-
Disable mise runtime updates in Renovate (
42e84a6) -
Remove .jules/bolt.md (
2ddd7fc) -
Remove mcp-name from README (
cbb5aa9) -
Security hardening from code audit (
f2c7af2) -
Testing improvement] Update patch_searxng_windows mock pattern (#426,
c7d0187) -
ci: Use pull_request_target for jobs requiring secrets (
44138fe) -
deps: Update dependency qwen3-embed to >=1.4.3 (#342,
a65d8ed)
Chores
-
Add glama.json for Glama directory listing (
d7d550f) -
Add jsonschema dependency for structured extraction (
accb383) -
Ignore PLR0913 for search tool to preserve MCP API schema (#454,
5a0987a) -
Remove .jules directory (bot artifact) (
698430d) -
Standardize repo files across MCP server portfolio (
9c5285a) -
Update uv.lock for markitdown[xlsx] dependency (
a77d940) -
deps: Bump pyopenssl in the uv group across 1 directory (#461,
069601e) -
deps: Update actions/download-artifact digest to 3e5f45b (#379,
efe04ba) -
deps: Update astral-sh/setup-uv digest to 37802ad (#380,
50978dd) -
deps: Update dawidd6/action-send-mail action to v15 (#386,
374b8ae)
Documentation
-
Add Pre-Phase + Phase 1 implementation plan (
bf43027) -
Add v2.14-v2.16 design spec (
41c6108) -
Fix 3 blockers + warnings in design spec (
38c285c) -
Update help docs for Phase 2 features and add plan (
5c16657) -
Update help docs for Phase 3 features (batch, HyDE, Jina) (
a74cc35) -
Update help docs for search filters and convert action (
bbbed10)
Features
-
Add batch extract with per-domain rate limiting (
94f6552) -
Add better-telegram-mcp to Also by section and mcp-name (
eb48c10) -
Add Glama.ai badge to README (
e1088d6) -
Add HyDE for docs search and version-specific docs discovery (
d833e0c) -
Add is_safe_local_path for local file validation (
1ed9453) -
Add Jina AI as priority #1 for embedding and reranking (
f4bccaa) -
Add LLM-powered structured data extraction (
d24853e) -
Add local file convert action with security validation (
d69130d) -
Add search filters (time_range, language, include/exclude domains) (
39f07a2) -
Add search strategies (query expansion, find similar, snippet enrichment) (
1b9d844) -
Add semantic reranking to web search results (
66d4824) -
Add URL normalization and per-domain result cap to search (
e8094eb) -
Testing Improvement] Add tests for start_auto_sync and stop_auto_sync (#422,
a6ae793) -
Tune SearXNG engine weights and default language to auto (
4659208) -
Wire Phase 2 actions (structured, similar, expand, enrich) (
76fb17d)
Detailed Changes: v2.13.0...v2.14.0
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 n24q02m/wet-mcp
Web search (embedded SearXNG), content extraction, and library docs indexing with hybrid search (FTS5 + semantic). Built-in Qwen3 embedding, no API keys required.
Related context
Beta — feedback welcome: [email protected]