Mirelo MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MIRELO_API_KEY | No | Mirelo API key (bearer token). If absent, the server still starts and advertises all tools; calls that need credentials return a missing-credential error. | |
| MIRELO_BASE_URL | No | Base URL for the Mirelo API. Must be an absolute http/https URL. Normalized (trailing slash stripped). | https://api.mirelo.ai |
| MIRELO_TIMEOUT_MS | No | Request timeout in milliseconds. Must be an integer in [1000, 600000]. | 60000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mirelo_text_to_sfx_generateB | Generate sound effects synchronously from a text prompt and return the result URLs. |
| mirelo_text_to_sfx_submitA | Submit an asynchronous Text-to-SFX generation job and return the job id and job URL for later polling. |
| mirelo_text_to_sfx_preflightA | Estimate the credit cost and processing time for a Text-to-SFX generation without generating audio. |
| mirelo_video_to_sfx_generateC | Generate a synced sound track for a supplied video synchronously and return the result URLs. Requires a video Input_Source and duration_ms. |
| mirelo_video_to_sfx_submitA | Submit a Video_To_SFX generation as an asynchronous job and return the job id and job URL for later polling. Requires a video Input_Source and duration_ms. |
| mirelo_video_to_sfx_preflightA | Estimate the credit cost and processing time for a Video_To_SFX generation without generating. Uses duration_ms and num_samples. |
| mirelo_extend_audio_generateA | Extend Audio (audio-only), synchronous: append newly generated audio to an existing audio input and return the result URL(s). |
| mirelo_extend_audio_submitA | Extend Audio (audio-only), asynchronous submission: submit an extend-audio job and return its job_id and job_url for later polling. |
| mirelo_extend_audio_preflightA | Extend Audio (audio-only) preflight: estimate the credit cost and processing time for an extend-audio request. |
| mirelo_extend_audio_with_video_generateA | Extend an existing audio input with newly generated audio conditioned by a video (synchronous). Returns result URLs. Requires audio and video Input_Sources and append_duration_ms (1000-57000 ms). Model v1.6 only. |
| mirelo_extend_audio_with_video_submitA | Submit an asynchronous Extend_Audio with-video job (append audio conditioned by a video). Returns a job_id and job_url to poll with mirelo_job_status. Requires audio and video Input_Sources and append_duration_ms (1000-57000 ms). Model v1.6 only. |
| mirelo_extend_audio_with_video_preflightA | Estimate the credit cost and processing time for an Extend_Audio with-video generation before committing. Requires append_duration_ms (1000-57000 ms); num_samples defaults to 1. Model v1.6 only. |
| mirelo_inpaint_audio_generateB | Synchronously replace a bounded segment of an audio clip with newly generated audio (Inpaint_Audio, audio-only). Returns the resulting audio URL(s). |
| mirelo_inpaint_audio_submitA | Submit an asynchronous Inpaint_Audio (audio-only) job that replaces a bounded audio segment, returning a job identifier to poll with mirelo_job_status. |
| mirelo_inpaint_audio_preflightA | Estimate the credit cost and processing time of an Inpaint_Audio (audio-only) request before generating. |
| mirelo_inpaint_audio_with_video_generateA | Synchronously replace a bounded segment of an audio clip with newly generated audio conditioned by a video (Inpaint_Audio, with-video). Requires audio and video Input_Sources and a segment. Returns the resulting audio URL(s). Model v1.6 only. |
| mirelo_inpaint_audio_with_video_submitA | Submit an asynchronous Inpaint_Audio (with-video) job that replaces a bounded audio segment conditioned by a video, returning a job identifier to poll with mirelo_job_status. Requires audio and video Input_Sources and a segment. Model v1.6 only. |
| mirelo_inpaint_audio_with_video_preflightA | Estimate the credit cost and processing time of an Inpaint_Audio (with-video) request before generating. Requires a segment; num_samples defaults to 1. Model v1.6 only. |
| mirelo_job_statusA | Poll the status of an asynchronous Mirelo generation job by its job_id via the shared GET /v2/jobs/{job_id} endpoint. Surfaces processing progress, succeeded result URLs, or the failure reason. |
| mirelo_create_asset_upload_slotA | Create an asset upload slot (POST /v2/assets) for a given content_type, returning an asset_id and a presigned upload_url. When an optional local file_path is provided, the file's bytes are uploaded to that URL so the asset_id is immediately usable in generation and editing operations. |
| mirelo_get_accountA | Retrieve the authenticated Mirelo account identity and available credit balance: id, email, credits_available, and overage_enabled. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 21 tools
Each tool targets a distinct operation: generation, preflight estimation, or asynchronous submission for specific audio tasks (extend, inpaint, text-to-sfx, video-to-sfx), with clear separation between audio-only and with-video variants. Additional tools for account, asset upload, and job polling are unique and non-overlapping.
All tools follow a consistent snake_case pattern with the 'mirelo_' prefix, using verb_noun combinations like 'extend_audio_generate' and 'job_status'. The naming is predictable and uniform across synchronous, preflight, and submit variants.
21 tools is slightly above the typical range, but each tool is justified for a comprehensive audio generation and editing service covering synchronous and asynchronous modes, preflight cost estimation, and support for multiple input types. The count is well-scoped and not excessive.
The tool set covers core generation and editing workflows (extend, inpaint, text-to-sfx, video-to-sfx), including cost estimates and async submission. Missing features include job cancellation, listing assets, and asset deletion, but these are minor gaps for the primary audio generation purpose.