PeerTube MCP for AI. Manage decentralized video feeds via your AI agent.

Q: How do I get a download link using generatevideodownload?

You pass the video ID and necessary tokens to generatevideodownload. The tool executes the request and returns a direct, usable URL for the file.

Q: Do I need to use getpublichlsplaylist for streaming?

Yes. For robust streaming playback, you must call getpublichlsplaylist because it provides the necessary HLS manifest that modern video players require.

Q: What's the first step to accessing private content?

First, you must obtain a user access token by calling getusertoken. Then, you can pass this token along with the necessary file token when using getprivatewebvideo.

Q: Can I check if video transcoding finished?

Yes. Use getcompletedjobs. This tool checks the status of background processing tasks, letting you know if a job succeeded or failed without manual intervention.

Q: How do I start with authentication using getlocaloauthclients?

First, run getlocaloauthclients to grab your client credentials. This returns the Client ID and Secret needed for secure connection. You use these details later when calling a tool to request a specific user access token.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

PeerTube MCP Server gives your AI agent direct access to the decentralized video ecosystem. Manage feeds and download content from PeerTube instances using natural language commands.

It lets you interact with a federated, open-source alternative to centralized platforms, handling everything from user registration to private file retrieval.

What your AI can do

Generate video download

Creates a direct, usable download link for a specified video file.

Get completed jobs

Checks the status of background tasks that require authentication to view results.

Get local oauth clients

Retrieves your local Client ID and Secret needed for OAuth 2.0 authorization flows.

+ 7 more capabilities included

Find public video streams

Use get_public_web_video to fetch a direct link for publicly available web-hosted videos.

Stream HLS playlists

Get the manifest file using get_public_hls_playlist, which is necessary for robust, streaming video playback.

Manage user accounts

Register new users or obtain access tokens needed to interact with private content via register_user and get_user_token.

Retrieve private files

Use get_private_web_video when you have a videoFileToken, allowing your agent access to protected media.

Check job status

Run get_completed_jobs to monitor whether background processes like transcoding finished successfully.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

PeerTube (YouTube Alternative) MCP Server: 10 Tools for Video Ops

These tools let you manage video feeds, download content, and handle user accounts across decentralized PeerTube instances using your AI client.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using PeerTube (YouTube Alternative) on Vinkius

Generate Video Download

Creates a direct, usable download link for a specified video file.

Get Completed Jobs

Checks the status of background tasks that require authentication to view results.

Get Local Oauth Clients

Retrieves your local Client ID and Secret needed for OAuth 2.0 authorization flows.

Get Private Web Video

Fetches a private web video file, requiring a specific videoFileToken for access.

Get Public Hls Playlist

Retrieves the manifest playlist necessary to stream public videos using HLS protocol.

Get Public Web Video

Gets a direct file link for any publicly available web video.

Get User Token

Acquires the necessary user access token to authorize subsequent API calls.

Get Video Comments Feed

Retrieves a complete feed of comments associated with a specific video ID.

Get Video Feeds

Fetches the core list and metadata for video feeds from your connected PeerTube...

Register User

Creates a new user account on the specified PeerTube instance.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The PeerTube integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "peertube-youtube-alternative": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the PeerTube tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"peertube-youtube-alternative": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with PeerTube (YouTube Alternative), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by PeerTube. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Manually checking decentralized media APIs is a pain.

Right now, getting video metadata means juggling multiple formats—checking RSS feeds for titles, hitting JSON endpoints for data payloads, and then figuring out if the stream link requires an HLS playlist or just a direct MP4 download. It's tedious copy-pasting across three different tabs.

With this MCP server, you just tell your agent what you need: 'Give me all the public video feeds.' The tool runs `get_video_feeds` and handles all the format parsing and aggregation for you. You get clean data, ready to use.

PeerTube MCP Server: Manage video ops from your chat.

You no longer have to manually run `get_local_oauth_clients` into a terminal and then copy-paste the resulting secrets into another system. The agent handles the entire sequence, making credential retrieval part of a simple conversation.

It boils down to this: you manage complex content pipelines—from user registration (`register_user`) to fetching private streams—using only natural language commands in your favorite client.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Listen up. The PeerTube MCP Server gives your AI agent direct access to the whole decentralized video ecosystem. You can manage feeds and download content from PeerTube instances using natural language commands. It lets you interact with a federated, open-source alternative, handling everything from user registration right through to private file retrieval.

When you use this server, your agent knows exactly how to operate across public streams, private accounts, and background tasks.

Video Discovery and Streaming

You want to check out what's happening online? You can first run get_video_feeds to pull the core list and metadata for video feeds from whatever PeerTube instance you connect to. If you just need a quick look at publicly available content, use get_public_web_video; that function grabs a direct file link for any web-hosted video.

For proper streaming playback, you gotta get the manifest file using get_public_hls_playlist. This retrieves the HLS playlist necessary to stream public videos robustly. To read what people are saying about a specific piece of media, your agent calls get_video_comments_feed, which pulls a complete feed of comments tied to a video ID.

Authentication and Account Management

If you're dealing with private or protected content, authentication is key. You can create a new user account on the specified PeerTube instance by running register_user. After that, your agent acquires the necessary access token using get_user_token to authorize all subsequent API calls.

For deeper integration, you'll need OAuth 2.0 credentials; run get_local_oauth_clients to retrieve your local Client ID and Secret for authorization flows. If the video itself is private, use get_private_web_video. This requires a specific videoFileToken to access protected media.

Content Retrieval and Status Checks

Once you've got the right links or tokens, getting the final content is straightforward. To pull the actual file for public videos, you rely on get_public_web_video. If you just need a single downloadable link for any video, generate_video_download creates that usable download URL.

Finally, if any process runs in the background—like transcoding a video or completing a complex federation task—you can check on its status using get_completed_jobs to monitor whether those jobs finished successfully and are ready for viewing.

Built · Hosted · Managed by Vinkius PeerTube MCP Server - Decentralized Video Feeds

Server ID 019e38d4-f173-73b8-a183-36d616f867b0

Vinkius Inspector

Compliance Grade F

Score 3.6/100

Report View Report ↗

Here's how it actually works

The bottom line is that you feed the server an instance URL and let your agent execute complex video operations through simple chat prompts.

First, subscribe to the server and provide your target PeerTube Instance URL.

Next, if you need private content or admin rights, use get_user_token to obtain a valid access token.

Finally, run commands like get_video_feeds or generate_video_download within your AI client using the established connection.

Who is this actually for?

This tool serves content creators, data scientists, and privacy advocates. You're the developer who needs to test decentralized APIs without opening a terminal. You're tired of centralized platform limitations and need reliable access to open-source video feeds.

DevOps Engineer

Uses get_local_oauth_clients and the token flow to test API integrations and manage credentials for automated content pipelines.

Data Scientist

Retrieves video metadata using get_video_feeds or analyzing comment streams with get_video_comments_feed for academic research on public discourse.

Privacy Advocate

Accesses decentralized media through a secure, AI-managed interface without relying on major tech company infrastructure. Uses register_user to establish accounts across multiple instances.

What Changes When You Connect

Access complex metadata using get_video_feeds. Instead of navigating multiple RSS or JSON endpoints, you ask your agent for the feed data directly. This handles pagination and format parsing automatically.

Stream videos reliably by calling get_public_hls_playlist. You get the HLS manifest needed for robust playback in any modern player, bypassing single-file download limitations.

Handle authentication securely with get_user_token. Your agent grabs the necessary token and keeps it ready for calls to both public and private tools like get_private_web_video.

Monitor large jobs using get_completed_jobs. You don't have to manually check a dashboard; just ask your agent, 'Did the transcoding job finish?' and get an immediate status update.

Build full user pipelines. Use register_user first, then use the resulting credentials to fetch content or manage feeds for that new account.

See it in action

01 01

A developer needs OAuth tokens

The dev needs client access data to build a third-party dashboard. Instead of checking documentation and manually hitting the API, they prompt their agent: 'Give me the local OAuth credentials.' The agent uses get_local_oauth_clients and returns the Client ID and Secret immediately.

02 02

A creator wants to analyze public discussions

A researcher wants to gauge sentiment on a popular video. They ask their agent to 'Get the comments feed for this video.' The agent runs get_video_comments_feed, returning structured data that can be immediately summarized or analyzed in bulk.

03 03

Finding and downloading private content

A user has a restricted link to internal footage. They tell their agent, 'Download the video at this token.' The agent uses get_private_web_video with the provided file token, bypassing public access restrictions.

04 04

Monitoring large content uploads

A team uploaded 50 videos for transcoding. Instead of logging into the admin panel repeatedly, they prompt their agent: 'What's the status of the video jobs?' The agent calls get_completed_jobs and gives a single, clear report on success/failure.

The honest tradeoffs

Assuming centralized behavior

Anti-pattern

Trying to treat PeerTube like YouTube by only asking for one generic 'video link' without specifying if the content is public or private.

The Fix

Always specify your intent. If you need a streamed file, use get_public_hls_playlist. If it’s restricted, make sure you run get_user_token first, then call get_private_web_video.

Forgetting the token flow

Anti-pattern

Attempting to use a tool like get_video_feeds without having already obtained and passed a valid user access token.

The Fix

The key is always authorization. Start by running get_user_token. This gives you the necessary credential to unlock almost all content tools.

Overlooking feed formats

Anti-pattern

Assuming that asking for 'the video list' returns everything in one neat package, only to find out it requires separate calls for JSON feeds and RSS feeds.

The Fix

Be specific. Use get_video_feeds for the core listing data, or use get_video_comments_feed if you only care about discussion threads.

When It Fits, When It Doesn't

Use this server if your workflow requires interaction with decentralized video content and its complex metadata structure. You need to: 1) Manage user accounts/tokens (register_user, get_user_token). 2) Handle both public streaming (HLS via get_public_hls_playlist) and private files (get_private_web_video). 3) Monitor background system processes (get_completed_jobs).

Don't use this if you simply need to embed a single video on a webpage. For that, direct integration or a simple URL is faster than setting up the full MCP flow. This toolset is for API-driven content management, not basic consumption.

Questions you might have

How do I get a download link using generate_video_download? +

You pass the video ID and necessary tokens to generate_video_download. The tool executes the request and returns a direct, usable URL for the file.

Do I need to use get_public_hls_playlist for streaming? +

Yes. For robust streaming playback, you must call get_public_hls_playlist because it provides the necessary HLS manifest that modern video players require.

What's the first step to accessing private content? +

First, you must obtain a user access token by calling get_user_token. Then, you can pass this token along with the necessary file token when using get_private_web_video.

Can I check if video transcoding finished? +

Yes. Use get_completed_jobs. This tool checks the status of background processing tasks, letting you know if a job succeeded or failed without manual intervention.

How do I start with authentication using get_local_oauth_clients? +

First, run get_local_oauth_clients to grab your client credentials. This returns the Client ID and Secret needed for secure connection. You use these details later when calling a tool to request a specific user access token.

Can I get video feeds in different formats like RSS or JSON using get_video_feeds? +

Yes, the function supports multiple output structures. Simply specify whether you need Atom, JSON, or XML format when calling it. This allows your agent to parse the feed data into whatever structure it needs.

What should I check if get_public_web_video fails? +

The tool returns an error code and a message indicating failure, so don't assume missing content. A 403 status usually means access is restricted, while a 404 means the video ID doesn't exist.

What happens if I try to register_user with bad input? +

The function returns an error detailing exactly what was wrong. You must correct the formatting—for example, ensuring a valid email structure or strong password requirements—before retrying.

How can I generate a direct download link for a PeerTube video? +

You can use the generate_video_download tool by providing the video's ID or UUID. The agent will return a muxed mp4 container link for downloading.

Can I register a new user account on my instance using the AI? +

Yes, if the instance allows public registration, you can use the register_user tool with a username, password, and email address.

How do I check if my video transcoding jobs are finished? +

Use the get_completed_jobs tool. It retrieves a list of all finished background jobs, allowing you to verify successful processing.

Connect to your AI in seconds.

Generate video download

Get completed jobs

Get local oauth clients

PeerTube (YouTube Alternative) MCP Server: 10 Tools for Video Ops

Make your AI actually useful.

Generate Video Download

Get Completed Jobs

Get Local Oauth Clients

Get Private Web Video

Get Public Hls Playlist

Get Public Web Video

Get User Token

Get Video Comments Feed

Get Video Feeds

Register User

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Manually checking decentralized media APIs is a pain.

PeerTube MCP Server: Manage video ops from your chat.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

A developer needs OAuth tokens

A creator wants to analyze public discussions

Finding and downloading private content

Monitoring large content uploads

The honest tradeoffs

Assuming centralized behavior

Forgetting the token flow

Overlooking feed formats

When It Fits, When It Doesn't

Questions you might have