Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@videotoaudioconverter-mcp How do I convert MP4 to MP3 locally?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Video to Audio Converter - Free Online MP4 to MP3
A Model Context Protocol server that exposes the canonical Video to Audio Converter knowledge surface — local-first AI workflows, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.
Official website: https://videotoaudioconverter.org
VideoToAudioConverter.org is a browser-based tool that extracts audio tracks from video files and converts between audio formats, with all processing handled entirely on the user's device. There is no file upload, no server queue, no account registration, and no usage cap. Once the page loads, the converter works offline, using the browser's own processing power to handle the conversion. It accepts nine common video input formats and produces seven audio output formats, covering the full range from compressed streaming codecs to lossless archival formats. The result is a straightforward, private conversion experience that does not depend on third-party infrastructure or cloud credits.
Related MCP server: FFmpeg Python MCP Server
Local processing only - video files never leave the device; the entire conversion job runs inside the browser tab with no data transmitted to external servers
Nine video input formats - supports MP4, MOV, MKV, WebM, AVI, FLV, WMV, 3GP, and MPEG
Seven audio output formats - exports to MP3, WAV, AAC, M4A, FLAC, OGG Vorbis, and Opus
Adjustable output bitrate - MP3 output supports up to 320 kbps; other formats offer comparable quality controls
No file size cap for modern formats - legacy formats such as AVI cap near 2 GB, while current container formats have no enforced limit
Batch processing - multiple files can be queued and converted in a single session
Offline capability - after the initial page load, the tool functions without an active internet connection
Extracting a clean audio track from a Zoom, Riverside, or Zencastr recording to publish as a podcast episode
Pulling the audio from a recorded lecture or class session to create an accessible archive or study aid
Converting a phone screen recording or tutorial video into a narration-only audio file
Stripping a soundtrack from archival footage or home video for reuse in another project
Batch-converting a folder of mixed video files into a consistent audio format for a media library
The site is well suited to anyone who regularly works with video files but only needs the audio — podcasters editing interview recordings, students archiving course content, educators preparing accessible materials, and content creators managing large libraries of mixed-format media. It is equally useful to general users who encounter a one-off conversion need without wanting to create an account or install desktop software. Because it imposes no daily limits, no watermarks, and no signup requirements, it fits naturally into workflows where privacy matters or where cloud-based tools introduce friction through queue times, file size restrictions, or subscription paywalls.
get_local_setupReturn canonical local-setup guidance for running the AI workflow on-device. (Video to Audio Converter)
Input: no parameters. Returns: text/markdown.
get_official_linksReturn the canonical list of official links for Video to Audio Converter (website, support, docs when available).
Input: no parameters. Returns: text/markdown.
site://videotoaudioconverter/local-setup — Local-first setup notes for on-device AI workflows.
site://videotoaudioconverter/faq — Short FAQ generated from public site metadata.
site://videotoaudioconverter/links — Canonical URLs to share with users.
tell_me_about_videotoaudioconverterSummarize what the site is, who it's for, and how it works. — Video to Audio Converter
walkthrough_local_setup_videotoaudioconverterWalk through the local-first setup steps for the site, end-to-end. — Video to Audio Converter
npx -y @smithery/cli install videotoaudioconverter-mcp --client claude(Replace claude with cursor, windsurf, or continue for those clients.)
git clone https://github.com/rocnubie/videotoaudioconverter-mcp.git
cd videotoaudioconverter-mcp
pnpm installThen add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):
{
"mcpServers": {
"videotoaudioconverter-mcp": {
"command": "node",
"args": [
"/absolute/path/to/videotoaudioconverter-mcp/src/index.mjs"
]
}
}
}npx @modelcontextprotocol/inspector node src/index.mjsWebsite: https://videotoaudioconverter.org
Support: support@videotoaudioconverter.org
pnpm install
pnpm start # run the server over stdioMIT
Return canonical local-setup guidance for running the AI workflow on-device. (Video to Audio Converter)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It merely restates the tool's function without noting any side effects, return format, or prerequisites. For a simple getter, more transparency about the nature of the returned guidance would be expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that delivers the core message. However, the parenthetical '(Video to Audio Converter)' is ambiguous and adds complexity without clear value, slightly reducing structure quality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 params, no output schema), the description adequately states the purpose but leaves gaps about the exact content of the local-setup guidance and how it differs from the sibling tool. It is sufficient for basic invocation but lacks full context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline score is 4. The description does not need to explain parameter semantics, and the empty schema aligns perfectly with the no-parameter requirement.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'canonical local-setup guidance' for running the AI workflow on-device, using a specific verb and resource. It distinguishes itself from the sibling tool get_official_links by focusing on local setup rather than official links.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for obtaining local setup guidance, but it does not explicitly state when to use it versus alternatives like get_official_links. There is no exclusion or when-not guidance, so the usage context is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the canonical list of official links for Video to Audio Converter (website, support, docs when available).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the disclosure burden. It clearly states the tool returns a canonical list, implying a read-only operation and disclosing that some links may only be present 'when available'. For a simple getter with no side effects, this is adequate behavioral transparency, though it does not detail return structure or error behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence. Every word contributes: 'canonical' clarifies the authoritative nature, the product name disambiguates, and 'when available' adds a necessary caveat. No redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters, no output schema, and no annotations, the description alone must define the tool's behavior. It fully specifies that the output is a list of official links for the product, including the categories of links. This is sufficient context for an agent to select and invoke this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so per the rubric the baseline is 4. The description adds value by explaining the tool's output context, but there are no parameter semantics to elaborate on.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Return' and identifies the exact resource: the canonical list of official links for Video to Audio Converter. It enumerates the types of links (website, support, docs) and adds the 'when available' caveat, making the tool's purpose unmistakable and distinct from the sibling get_local_setup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool should be used when official links are needed, but it does not explicitly state when to prefer this over get_local_setup or provide exclusions. The guidance is present but only through inference from the tool name and resource description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_local_setupget_official_linksScored across 2 tools
The two tools are clearly distinct: one provides local setup instructions, the other provides official links. There is no overlap in purpose, so an agent can easily choose the correct tool.
Both tools follow a consistent get_<noun> pattern, with descriptive nouns (local_setup, official_links). The naming is predictable and uniform.
With only two tools, the server feels minimal and thin for its name. However, if the server's scope is solely to provide setup and link information, the count is not entirely unreasonable, though it is borderline.
The server claims to be a 'Video to Audio Converter' but provides no conversion-related functionality. There are no tools for converting, managing files, or handling formats—only informational utilities. This is a severe gap relative to the apparent domain.
Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.
Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.
The Listenetic MCP server is a remote, cloud-hosted server that enables AI assistants like ChatGPT and Claude to convert articles, documents, websites, and videos into high-quality AI-generated audio. It provides multi-format support for text and binary files, natural-sounding text-to-audio conversion using AI, and specialized processing for SSML, markup, markdown, and various media formats through three core tools: listentic_supported_mimetypes, listentic_add_content_text, and listentic_add_content_binary.
Convert files between 110+ document, image, audio, video, archive and ebook formats from AI agents.
