9 tools for AI assistants: subtitle convert/shift/merge (srt/vtt/sbv/ass), multilingual text count, LLM token estimation, JSON tools, hashes. Zero telemetry.
Scored across 9 tools
Each tool has a clearly distinct purpose: subtitle operations are separated by conversion, merging, shifting, and statistics, while text, JSON, hashing, token estimation, and case transformation do not overlap. No two tools appear to perform the same action.
All names use snake_case, but the structure is mixed: some are noun_verb (case_transform, subtitle_convert, text_count), one is verb_noun (estimate_tokens), and two use a generic _tool suffix (hash_tool, json_tool). This is readable but not a predictable convention.
Nine tools is well within a reasonable range for a utility server. Each tool covers a distinct operation, and the set does not feel bloated or artificially thin.
Core subtitle file operations (convert, merge, shift, stats) and supporting text/JSON/hash utilities are covered. Some gaps exist, such as subtitle editing/splitting and JSON set/update operations, but they are manageable for typical workflows.
Transform case (upper/lower/title/camel/snake/...).
Inputs: to (required), text (required).
Estimate LLM tokens for gpt/claude/gemini.
Inputs: text (required), model.
Validate/format/minify/sort/get on JSON.
Inputs: op (required), json (required), path, indent.
Convert subtitles between srt/vtt/sbv/ass formats.
Inputs: to (required), content (required), from.
Merge two subtitle files, sorted by time.
Inputs: a (required), b (required), output_format.
Shift all subtitle cues by milliseconds.
Inputs: ms (required), content (required).
Stats: format, cue count, duration, chars.
Inputs: content (required).
Multilingual word/char/sentence count (CJK-aware).
Inputs: text (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.