Skip to the page
Get started free

SpecStream for DR Tulu

SpecStream is the live web data engine for teams and agents. Change the Serper and Jina Reader addresses in DR Tulu's MCP backend, and the deep research agent searches and reads pages through SpecStream, in the reply shapes its tools already parse.

Read the guide

What you get

Two addresses
google.serper.dev/search becomes api.specstream.ai/serper/search, and r.jina.ai becomes api.specstream.ai/jina. The model, prompts and tool parser stay as they are.
One key for both
Your SpecStream key goes in SERPER_API_KEY and JINA_API_KEY. One balance pays for every search and every page a run reads.
Benchmark runs included
The repository's evaluation scripts use the same two functions, so a SimpleQA or WebWalker run goes through SpecStream with no other change.

Set it up

  1. Get a SpecStream key on the Search API screen of your workspace.
  2. In dr-tulu/agent, change the Serper address in serper_apis.py and the Jina Reader address in jina_apis.py to SpecStream's routes.
  3. Set SERPER_API_KEY and JINA_API_KEY to your key in .env, restart the MCP backend with --no-cache, and ask.

The full setup guide has every step, with what to do if something doesn’t arrive.

Also in Agent frameworks & builders

The same live web data, in the other tools of this kind.

Live web data, in DR Tulu.

Ask in your own words for companies, places, people, filings or anything else the web lists.

Read the guideTalk to a human