OpenCode CLI multi-expert setups need a shared web-search layer so each expert agent sees the same fresh baseline. Scavio's hosted MCP at `https://mcp.scavio.dev/mcp` plugs in once and exposes search to every expert. This tutorial covers config, expert prompt setup, and a routing pattern.
Prerequisites
- OpenCode CLI installed
- Scavio API key
Walkthrough
Step 1: Add Scavio MCP to OpenCode config
Single endpoint, single API key.
JSON
// ~/.opencode/config.json
{
"mcpServers": {
"scavio": {
"url": "https://mcp.scavio.dev/mcp",
"apiKey": "${SCAVIO_API_KEY}"
}
}
}Step 2: Define expert prompts
One markdown file per expert role.
# experts/seo-expert.md
You are an SEO expert. Always search Scavio for current SERP data before answering.
# experts/code-expert.md
You are a code expert. Search Scavio for current docs and GitHub issues.Step 3: Wire up routing
OpenCode routes user queries to the right expert.
# experts/router.md
Classify the query: SEO -> seo-expert, code -> code-expert, default -> generalist.Step 4: Test with a SEO query
Verify Scavio is called with the right query.
Bash
$ opencode 'rank top 5 cars 2026'
# router -> seo-expert
# seo-expert calls Scavio /api/v1/google
# returns SERP plus AI Overview citationsStep 5: Test with a code query
Verify code expert pulls GitHub via SERP.
Bash
$ opencode 'find async-await issues in tokio repo'
# router -> code-expert
# code-expert calls Scavio with site:github.com/tokio-rs filterPython Example
Python
# OpenCode is a CLI; use Python to orchestrate experts directly via Scavio
import os, requests
API_KEY = os.environ['SCAVIO_API_KEY']
EXPERTS = {'seo': 'site: in any', 'code': 'site:github.com'}
def expert_search(role, q):
scope = EXPERTS.get(role, '')
r = requests.post('https://api.scavio.dev/api/v1/google',
headers={'x-api-key': API_KEY},
json={'query': f'{q} {scope}'}).json()
return r.get('organic_results', [])[:10]JavaScript Example
JavaScript
const API_KEY = process.env.SCAVIO_API_KEY;
const EXPERTS = { seo: '', code: 'site:github.com' };
export async function expertSearch(role, q) {
const scope = EXPERTS[role] || '';
const r = await fetch('https://api.scavio.dev/api/v1/google', { method:'POST', headers:{'x-api-key':API_KEY,'Content-Type':'application/json'}, body: JSON.stringify({ query: `${q} ${scope}` }) });
return (await r.json()).organic_results || [];
}Expected Output
JSON
OpenCode CLI routes user queries to the right expert; each expert calls Scavio MCP for fresh data. Same fresh baseline across all experts.