Connect OpenCode to Supadata
Set up in minutes
Choose where it runs
On your computer through your own OpenCode, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Supadata
A preset of real Supadata operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Supadata
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your OpenCode first calls in. opencode mcp add only saves the config. OpenCode connects when it starts — run opencode, or restart a running one.
1. Run this in your terminal
2. Choose Remote and paste your server URL
3. Choose No when asked about OAuth authentication — the link itself is the key
<your-link> is your personal server URL — setup mints it for you.
Tools OpenCode gets
Supadata
21 toolsGet metadata for a YouTube video.
Get metadata for a YouTube playlist.
Get video IDs from a YouTube playlist.
Get metadata for a YouTube channel.
Get video IDs from a YouTube channel.
Get transcript from YouTube video in various formats and languages. If the `lang` parameter is not provided or the transcript is not available in the requested language, the API defaults to the first available language.
Translate YouTube video transcript into different languages.
Create a batch job to get transcripts of multiple YouTube videos. Batches created from a playlist or channel include regular videos only (Shorts and live streams are skipped).
Create a batch job to fetch metadata of multiple YouTube videos. Batches created from a playlist or channel include regular videos only (Shorts and live streams are skipped).
Get the status and results of a YouTube batch job.
Search YouTube for videos, channels, and playlists with advanced filters.
Extract content from any web page to Markdown format.
Extract all links found on a whole website.
Create a crawl job to extract content from all pages on a website.
Get the status and results of a crawl by job ID.
Get transcript from a supported video platform (YouTube, TikTok, Twitter, Instagram, Facebook) or file URL. If the video is too large to return transcript immediately, request returns a job ID. Use the `/transcript/:jobId` endpoint to get job results.
Get results for a transcript job by job ID.
Fetch metadata from any supported internet media including YouTube, TikTok, Instagram, Twitter/X and Facebook posts. Returns unified metadata with a predictable structure across all platforms.
Use AI to analyze video content and extract structured data. Provide either a prompt describing what to extract, a JSON Schema for the output format, or both. Supports YouTube, TikTok, Instagram, Twitter/X, and Facebook videos, or a direct video file URL. Videos up to 3 hours (180 minutes) and files up to 2 GB are supported; the whole video is analyzed (1 frame per second up to 80 minutes, a lower evenly-spaced frame rate beyond). Over-limit YouTube and file URLs are rejected with 400 before a job is created. Returns a job ID for asynchronous processing. Use the `/extract/:jobId` endpoint to poll for results.
Get results for an extract job by job ID.
Retrieve organization details, plan information, and credit usage.
About OpenCode
Frequently asked questions
More ways to connect
More tools for OpenCode
Use Supadata with other agents
Open your OpenCode agent in one click.
NoClick runs OpenCode for you with Supadata wired in as tools. Connect your account and run.