Connect OpenCode to Bright Data
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 Bright Data
A preset of real Bright Data operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Bright Data
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
Bright Data
20 toolsRun a search engine request using your SERP zone. Usage is billed by Bright Data.
Fetch the result of an asynchronous SERP request.
List the datasets available from Bright Data.
List dataset snapshot metadata, optionally filtered by dataset or view.
Get a dataset snapshot’s metadata.
Count dataset download parts using the same format and batch size as the download.
List the account’s saved dataset views.
List scrapers configured on the connected account, with their input schemas.
Start a scraper job and return its snapshot ID. Bright Data bills the collection; this operation does not wait for completion.
Check whether a scraper snapshot is starting, running, ready, failed or canceled.
Download collected records as JSON data or an NDJSON/CSV file. Use a ready snapshot; large snapshots can be downloaded in parts.
List one page of scraper snapshots. Increase skip by limit to retrieve the next page.
Retrieve the collection logs for a scraper snapshot.
Count the download parts for a scraper snapshot.
Download the original scraper inputs as a CSV file.
Pause a running collection.
Resume a paused collection.
Cancel a running collection.
Rerun a previous collection using its stored inputs. Bright Data bills the new collection.
Check a delivery job’s status and delivered files.
About OpenCode
Frequently asked questions
More ways to connect
More tools for OpenCode
Use Bright Data with other agents
Open your OpenCode agent in one click.
NoClick runs OpenCode for you with Bright Data wired in as tools. Connect your account and run.