MCP SERVER
Web scraping for OpenAI Codex
Give Codex reliable web access through MCP.
Codex supports MCP servers in the CLI and IDE extension using shared config.toml configuration. Add webclaw-mcp and Codex can fetch live documentation, scrape protected pages, summarize sources, and extract structured data while it edits your codebase.
Setup
~/.codex/config.toml
[mcp_servers.webclaw]
command = "webclaw-mcp"
[mcp_servers.webclaw.env]
WEBCLAW_API_KEY = "wc_..."Why webclaw for Codex
- Fits Codex's MCP config.toml format
- Works from both Codex CLI and IDE extension configuration
- Fast scrape and search tools without browser setup
- LLM-ready markdown keeps Codex context focused
Common use cases
- Let Codex inspect current docs before changing code
- Research libraries, API references, and migration guides
- Scrape product pages or support docs into implementation notes
- Build repeatable web-data workflows as coding tasks
Frequently asked questions
Where do I configure webclaw for Codex?
Add a [mcp_servers.webclaw] table to ~/.codex/config.toml, or to a project-scoped .codex/config.toml in a trusted project. Codex CLI and the IDE extension share this configuration.
Can I add webclaw with the Codex CLI instead of editing TOML?
Yes. Codex also supports codex mcp add for managing MCP servers from the CLI. Editing config.toml gives you the exact final configuration in one place.
OTHER INTEGRATIONS