Lunara MCP
An MCP server for automated subtitle production that accepts audio or video uploads and returns written-language subtitle tracks plus translations with preserved ASR text and timings. It supports tools for uploading media, starting jobs, polling status, and downloading finished SRT files or cue data.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://lunaraai.cc/mcpWhat you can do with it
- Upload audio or video files for subtitle generation
- Start subtitle pipelines and poll job status
- Download finished SRT files or individual cues
- Retrieve organization glossaries for consistency
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- lunara 1.0.0
- MCP protocol
- 2025-06-18
- Tools
- 20 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {
"listChanged": false
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
20 advertised
lunara_list_tools
Return every subtitle tool Lunara exposes, with the minutes each one costs. Call this first when you are unsure which tool fits.
{
"type": "object",
"properties": {},
"additionalProperties": false
}{
"title": "List Lunara tools",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_get_job
Return the state of a subtitle job: status, progress, whether the SRT is ready, and how many cues it has. Poll this after lunara_upload_video.
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job id returned by lunara_upload_video."
}
},
"additionalProperties": false
}{
"title": "Get subtitle job",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_get_srt
Return the subtitle file for a finished job. One line per cue. Use track="secondary" for the translated track (English by default).
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job id."
},
"track": {
"enum": [
"primary",
"secondary"
],
"type": "string",
"description": "primary = the written-language track; secondary = the translation."
}
},
"additionalProperties": false
}{
"title": "Download SRT",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_list_cues
Return subtitle cues for a job as timestamps plus text, so you can inspect or reference individual lines before proposing edits.
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job id."
},
"limit": {
"type": "integer",
"maximum": 500,
"minimum": 1,
"description": "How many cues to return. Default 100."
},
"offset": {
"type": "integer",
"minimum": 0,
"description": "Skip this many cues. Default 0."
}
},
"additionalProperties": false
}{
"title": "List cues",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_start_subtitle_job
Run the full eight-layer subtitle pipeline on an audio or video URL you can already host. Produces a written-language track and a translated track. Prefer lunara_upload_video when the file is local.
{
"type": "object",
"required": [
"audioUrl"
],
"properties": {
"audioUrl": {
"type": "string",
"description": "A URL Lunara can download (public or pre-signed)."
},
"spokenLang": {
"type": "string",
"description": "What the speaker is speaking, e.g. yue-Hant-HK. Defaults to primaryLang."
},
"primaryLang": {
"enum": [
"zh-Hant",
"yue-Hant",
"zh-CN",
"en",
"ja",
"ko"
],
"type": "string",
"description": "Language of the written track. Default yue-Hant."
},
"secondaryLang": {
"enum": [
"zh-Hant",
"yue-Hant",
"zh-CN",
"en",
"ja",
"ko"
],
"type": "string",
"description": "Language of the translated track. Default en."
}
},
"additionalProperties": false
}{
"title": "Start a subtitle job from a URL",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false,
"lunara/costMinutes": 5
}lunara_subtitle_from_url
Start a persisted subtitle job from a URL you already host — no upload needed. Returns a job id; poll lunara_get_job every 15–30 s until status is "completed", then call lunara_get_srt. Prefer this over lunara_upload_video whenever the media is reachable by URL.
{
"type": "object",
"required": [
"audioUrl"
],
"properties": {
"audioUrl": {
"type": "string",
"description": "Direct HTTP(S) URL to the audio or video file. Must be downloadable by our server."
},
"filename": {
"type": "string",
"description": "Display name for the result. Defaults to the URL basename."
},
"spokenLang": {
"type": "string",
"description": "What the speaker is speaking, e.g. yue-Hant-HK. Defaults to auto-detect."
},
"primaryLang": {
"enum": [
"zh-Hant",
"yue-Hant",
"zh-CN",
"en",
"ja",
"ko"
],
"type": "string",
"description": "Language of the written track. Default yue-Hant."
},
"secondaryLang": {
"enum": [
"zh-Hant",
"yue-Hant",
"zh-CN",
"en",
"ja",
"ko"
],
"type": "string",
"description": "Language of the translated track. Default en."
}
},
"additionalProperties": false
}{
"title": "Subtitles from a URL",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false,
"lunara/costMinutes": 5
}lunara_upload_video
Reserve an upload slot and return the object key plus a signed URL per part. After uploading the bytes call lunara_finish_upload. Use this for a file you hold locally.
{
"type": "object",
"required": [
"filename",
"mime",
"sizeBytes"
],
"properties": {
"mime": {
"type": "string",
"description": "MIME type, e.g. audio/mpeg, video/mp4."
},
"filename": {
"type": "string",
"description": "Original filename, used for the download name."
},
"projectId": {
"type": "string",
"description": "Project to upload into. Omit to let Lunara reuse the most recent project for this organisation."
},
"sizeBytes": {
"type": "integer",
"minimum": 1,
"description": "Exact file size in bytes."
},
"primaryLang": {
"enum": [
"zh-Hant",
"yue-Hant",
"zh-CN",
"en",
"ja",
"ko"
],
"type": "string",
"description": "Written-track language. Default yue-Hant."
},
"secondaryLang": {
"enum": [
"zh-Hant",
"yue-Hant",
"zh-CN",
"en",
"ja",
"ko"
],
"type": "string",
"description": "Translated-track language. Default en."
},
"clientOperationId": {
"type": "string",
"description": "Idempotency key. Reuse the same value to retry without creating a second upload."
}
},
"additionalProperties": false
}{
"title": "Upload a video for subtitling",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false,
"lunara/costMinutes": 5
}lunara_finish_upload
Tell Lunara the bytes are uploaded so the pipeline can start. Returns the job id to poll with lunara_get_job.
{
"type": "object",
"required": [
"videoId",
"uploadId",
"key",
"durationMs",
"parts"
],
"properties": {
"key": {
"type": "string",
"description": "The object key."
},
"parts": {
"type": "array",
"items": {
"type": "object",
"required": [
"PartNumber",
"ETag"
],
"properties": {
"ETag": {
"type": "string"
},
"PartNumber": {
"type": "integer",
"minimum": 1
}
},
"additionalProperties": false
},
"description": "Uploaded parts, each { PartNumber, ETag }."
},
"videoId": {
"type": "string",
"description": "The video id from lunara_upload_video."
},
"uploadId": {
"type": "string",
"description": "The multipart upload id."
},
"durationMs": {
"type": "integer",
"minimum": 1,
"description": "Media duration in milliseconds."
}
},
"additionalProperties": false
}{
"title": "Finish an upload",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_get_glossary
Return the proper nouns Lunara has learned for this org, so names are spelled consistently across tracks.
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 500,
"minimum": 1,
"description": "Default 100."
}
},
"additionalProperties": false
}{
"title": "Get the project glossary",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_transcribe
Run speech recognition only — no rewrite, no translation. Returns timed segments. Use this when you want the transcript itself, or when you plan to pick a later stage yourself.
{
"type": "object",
"required": [
"audioUrl"
],
"properties": {
"audioUrl": {
"type": "string",
"description": "Direct HTTP(S) URL to the audio or video file."
},
"spokenLang": {
"type": "string",
"description": "What the speaker is speaking, e.g. yue-Hant-HK. Defaults to auto-detect."
}
},
"additionalProperties": false
}{
"title": "Transcribe audio",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 3
}lunara_translate
Translate the text of an existing job’s cues into another language. Every cue boundary and timestamp is preserved; only the text changes. Use this instead of translating yourself so the timing contract holds.
{
"type": "object",
"required": [
"jobId",
"targetLang"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job whose cues to translate."
},
"track": {
"enum": [
"primary",
"secondary"
],
"type": "string",
"description": "Which track to read. Default primary."
},
"targetLang": {
"enum": [
"zh-Hant",
"en",
"ja",
"ko"
],
"type": "string",
"description": "Target language."
}
},
"additionalProperties": false
}{
"title": "Translate a cue list",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 3
}lunara_rewrite
Turn spoken Cantonese cue text into written Chinese. Every cue boundary and timestamp is preserved. Deliberate mispronunciations are never corrected, and proper nouns are protected.
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job whose cues to rewrite."
},
"track": {
"enum": [
"primary",
"secondary"
],
"type": "string",
"description": "Which track to read. Default primary."
}
},
"additionalProperties": false
}{
"title": "Rewrite spoken → written",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 3
}lunara_segment
Approximate split, not audio-grounded segmentation: cue text is divided at clause punctuation and each piece receives a share of the original span proportional to its character count. The words are not changed. Timings are estimated, so treat them as a reading aid rather than a re-alignment — use lunara_start_subtitle_job if you need timing derived from the audio.
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job whose cues to re-cut."
},
"track": {
"enum": [
"primary",
"secondary"
],
"type": "string",
"description": "Which track to read. Default primary."
},
"maxCueMs": {
"type": "integer",
"maximum": 15000,
"minimum": 500,
"description": "Duration ceiling per cue in ms. Default 7000."
}
},
"additionalProperties": false
}{
"title": "Split cues at punctuation",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 1
}lunara_glossary_extract
Find candidate proper nouns in a job’s cues, ranked by frequency, with the first cue they appear in. Suggestions for a glossary, not corrections — nothing is rewritten.
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job whose cues to scan."
},
"limit": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "Maximum terms to return. Default 50."
}
},
"additionalProperties": false
}{
"title": "Extract proper nouns",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 1
}lunara_guide
Returns a step-by-step guide written to be read by a human, not by you. Call this when someone asks "how do I use this", "what can it do", "how do I get started", or when you need to explain the workflow rather than execute it. Pass journey="first_subtitle" for the end-to-end path, "api_key" for credential setup, "languages" for what is supported, or "limits" for what it cannot do. Answer the person with this text rather than paraphrasing from memory.
{
"type": "object",
"required": [],
"properties": {
"journey": {
"enum": [
"first_subtitle",
"api_key",
"languages",
"limits",
"edit_subtitles",
"agent"
],
"type": "string",
"description": "Which journey to explain. first_subtitle: upload to finished file. api_key: getting a credential. languages: what it does and does not handle. limits: honest boundaries. edit_subtitles: fixing a line after the fact. agent: putting this on an AI agent rather than doing it by hand."
}
},
"additionalProperties": false
}{
"title": "How to use Lunara — a guide you can relay to a person",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_get_queue
How many transcription jobs are running and whether a new one can be accepted. Call this before lunara_start_subtitle_job or lunara_subtitle_from_url if you are submitting several jobs — when saturated, wait the retryAfterSeconds rather than retrying immediately.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}{
"title": "Pipeline queue depth",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_qa_contract
Run the contract gate over both tracks: ASR text and timings byte-exact, cue length bounds, no empty cues. Returns pass/fail per rule. Free, because refusing a broken track should never cost the caller money.
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job to validate."
},
"track": {
"enum": [
"primary",
"secondary",
"both"
],
"type": "string",
"description": "Which track to check. Default both."
}
},
"additionalProperties": false
}{
"title": "Check the subtitle contract",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_probe_media
Return duration, dimensions, codecs and container for a URL, plus whether the audio is mono 16 kHz already. Call this before choosing an ASR engine.
{
"type": "object",
"required": [
"mediaUrl"
],
"properties": {
"mediaUrl": {
"type": "string",
"description": "URL to probe."
}
},
"additionalProperties": false
}{
"title": "Probe media",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_get_coverage
Report how much of the source timeline the subtitles cover, and list suspicious gaps longer than a second. Use before shipping a long video.
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job to inspect."
}
},
"additionalProperties": false
}{
"title": "Delivery coverage",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}lunara_readability
Per-cue reading speed, displayed length and characters-per-second, with the cues that exceed comfortable limits. Mirrors the metrics shown in the editor.
{
"type": "object",
"required": [
"jobId"
],
"properties": {
"jobId": {
"type": "string",
"description": "The job to measure."
},
"track": {
"enum": [
"primary",
"secondary"
],
"type": "string",
"description": "Default primary."
}
},
"additionalProperties": false
}{
"title": "Readability report",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false,
"lunara/costMinutes": 0
}Prompts
Not advertised
Resources
Not advertised
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 873 ms
- 95th percentile latency
- 873 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 873 ms · metadata changed · 20 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http lunara-mcp https://lunaraai.cc/mcpCodex
codex mcp add lunara-mcp --url https://lunaraai.cc/mcpCursor
{
"mcpServers": {
"lunara-mcp": {
"url": "https://lunaraai.cc/mcp"
}
}
}Cline
{
"mcpServers": {
"lunara-mcp": {
"type": "streamableHttp",
"url": "https://lunaraai.cc/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"lunara-mcp": {
"type": "http",
"url": "https://lunaraai.cc/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http lunara-mcp https://lunaraai.cc/mcpClaude Desktop
{
"mcpServers": {
"lunara-mcp": {
"url": "https://lunaraai.cc/mcp"
}
}
}Windsurf
{
"mcpServers": {
"lunara-mcp": {
"serverUrl": "https://lunaraai.cc/mcp"
}
}
}Let your agent find its tools
Find servers like Lunara MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.