jellyctrl v0.4.3

Full Changelog: v0.4.2...v0.4.3

jellyfin-mcp v0.4.2

Full Changelog: v0.4.1...v0.4.2

v0.4.1

Patch release for jellyctrl.

• Adds repeatable npm publishing with audit and package payload checks.
• Updates dependency locks so full npm audit is clean.
• Keeps the existing jellyctrl and compatibility entrypoints intact.

v0.4.0

Added

• 10 new tools since the v0.3.0 npm publish (46 to 56 total):
  • Continue Watching management: jellyfin_preview_continue_watching_clear,
    jellyfin_clear_continue_watching, jellyfin_clear_series_continue_watching,
    jellyfin_clear_episode_continue_watching_except_latest
  • Resume state and history: jellyfin_set_resume_position,
    jellyfin_get_watch_history, jellyfin_get_user_item_data
  • Bulk session control: jellyfin_pause_all_sessions,
    jellyfin_stop_all_sessions, jellyfin_message_all_active_sessions
• MCP tool annotations on all 56 tools: readOnlyHint: true on read-only
  tools, destructiveHint: true on destructive ones (user deletion, password
  reset, shutdown/restart, stopping sessions, resume-state clears, Quick
  Connect authorization), so MCP clients can route destructive calls to human
  approval. The confirm: true gate remains as a second layer.

Fixed

• Strip the draft-07 $schema the MCP SDK stamps on tool schemas; Anthropic
  rejects it when the full tool set is sent (e.g. on subagent spawns).
• JELLYFIN_TIMEOUT is validated: non-numeric, zero, or negative values now
  warn on stderr and fall back to the 30s default instead of producing a NaN
  that aborted every request after ~1ms.
• Server name and version are derived from package.json instead of
  duplicated literals, so the advertised MCP version can no longer drift from
  the published package version.

Security

• JELLYFIN_VERIFY_SSL=false now relaxes TLS certificate validation for the
  Jellyfin connection only, via a per-request undici dispatcher, instead of
  the process-global NODE_TLS_REJECT_UNAUTHORIZED which disabled validation
  for every outbound TLS connection.
• Upstream Jellyfin error response bodies are no longer returned to the MCP
  client; results carry the status summary only and the full body is logged
  to stderr for operators.
• jellyfin_set_user_password now warns (tool description and README) that
  the plaintext password transits the LLM conversation and provider logs.

Changed

• CI: the test step no longer uses continue-on-error, so test failures fail
  the build and gate the publish job.

v0.3.0 - discovery tools + Quick Connect

First tagged release. package.json is 0.3.0; tag catches GitHub up.

New in 0.3.0 (5 tools)

• jellyfin_get_resume_items - in-progress items with resume position (sec)
• jellyfin_get_next_up - next unwatched episode per series (user-scoped)
• jellyfin_get_similar_items - built-in recommender with optional user context
• jellyfin_quick_connect_status - server enabled flag
• jellyfin_quick_connect_authorize - approve a pending code (confirm-gated; one-time code never echoed back)

Also in this release

• CodeRabbit review follow-up: reject blank IDs, redact codes from authorize error paths
• Toolchain + SDK majors upgraded
• Item/UserItemData types tightened so discovery tools don't need structural casts

Since v0.2.0 recap

v0.2.0 added 16 tools (deeper playback, user-data writes, playlists, collections, confirm gates on destructive ops). Combined with v0.3.0 the server exposes the full set documented in the README.

Install

See the README for Claude Desktop, Claude Code, OpenClaw, Hermes Agent, and Codex CLI setup.

Tests

34 tests passing (client URL-encoding + tool-level handler tests including Quick Connect confirm gate and code-redaction).