SpecStream for Every Code
SpecStream is the live web data engine for teams and agents. The Codex fork asks SpecStream for live web data from the terminal. It searches the live web, reads whole pages and builds lists of records, with the price shown before any list runs.
What you get
- One table in config.toml
- An [mcp_servers.specstream] table with the server address and bearer_token_env_var keeps your key out of the file.
- Search and read in one session
- search_web answers from the live web, and read_pages returns the main text of up to 20 pages or documents in one call.
- Paid work only when you allow it
- Deep Search quotes the most a list can cost and waits for your approval. disabled_tools can keep it out of Every Code entirely.
Set it up
- Create a SpecStream API key and set it as SPECSTREAM_API_KEY in your shell profile.
- Add an [mcp_servers.specstream] table with url and bearer_token_env_var to ~/.code/config.toml.
- Check it with code mcp list, then ask in an Every Code session.
The full setup guide has every step, with what to do if something doesn’t arrive.
Live web data, in Every Code.
Ask in your own words for companies, places, people, filings or anything else the web lists.