Scrapfly · Codex
Add the Scrapfly MCP server to Codex
Scrape websites, extract structured data and collect web content at scale.
1. Add the server
Run in your terminal
# ~/.codex/config.toml [mcp_servers.scrapfly] command = "npx" args = ["-y", "scrapfly-mcp"]
Scopes, env vars, OAuth and limits: Codex MCP config guide
2. Sign in
Run codex mcp login <name> to complete OAuth for a remote server. Scrapfly runs locally; set any credentials Scrapfly asks for before starting Codex.
3. Try it
Ask Codex for something Scrapfly can do. Scrape websites, extract structured data and collect web content at scale. Approve the first tool call and check the result before allowing write actions automatically.
- · Each server is a [mcp_servers.<name>] table in config.toml.
- · Use enabled_tools or disabled_tools to keep the tool list short.
Get the weekly agent stack update
New official MCP servers, spec changes and harness releases, checked against the source. One email a week, no fluff.
FAQ
- How do I add the Scrapfly MCP server to Codex?
- Run: # ~/.codex/config.toml …. Run codex mcp login <name> to complete OAuth for a remote server.
- Is this the official Scrapfly MCP server?
- Yes. It is published by Scrapfly as io.scrapfly.mcp/mcp in the official MCP registry.
- Does the Scrapfly MCP server need an API key?
- It runs locally from a package. See Scrapfly's docs for any credentials it needs.
Links
Scrapfly in other clients
More web search & scraping for Codex
Work at Scrapfly?
Feature Scrapfly across the directory and its category from $49/month.
Reviewed Oct 5, 2026. Command generated from the registry record and checked against Codex's documented syntax.