qbash Connectors / Brave Search

Brave Search MCP serverand Python AI tasks

qbash hosts a Brave Search MCP server you can use in Claude, ChatGPT, Codex, Cursor, Grok Bot and Muse. Developers use qbash Tasks to write cloud-hosted Python functions that pair Brave Search with models such as Claude and GPT.

Connect Brave Search free

Add the qbash MCP

Use Brave Search from Claude Code, Codex, Cursor and other MCP clients. Connect Brave Search in qbash, and your agent can work with its data and build Tasks that call it.

claude mcp add --transport http qbash https://mcp.qbash.com/mcp

Then run /mcp in Claude Code and sign in with qbash.

Search one page of web results. Pages may overlap
Search one page of news results. Endpoint access depends on the selected plan
Search one page of video results. Pages may overlap
Search images in a single unpaginated request
Suggest query completions. Rich suggestions require the corresponding plan
Suggest spelling corrections for a query

Read the docs

Write a Brave Search task in Python

A qbash Task is a Python function hosted in the cloud. Python is the runtime and defines the process, and built-in inline prompts run on leading models such as Claude, GPT, Gemini and Grok.

Run a Task on a schedule, from an HTTP request or when a connected app sends an event. Your agents and chat tools call it over MCP.

Each run is logged with its inputs and results, and you can turn data logging off for any Task. Every Task has version control, and each run is locked to the version it ran.

Review search results for a research brief

Read one page of web results and ask a saved prompt to summarize their cited sources.

qbash Tasks Python AI SDK

main.py
page = qbash.integrations.brave_search.web_search(q="Brave Search API documentation", count=5)
results = page["results"]
if results:
    result = qbash.ai.run_prompt(slug="brave-search-research-brief", variables={"results": results})
    qbash.output(result)
else:
    qbash.output("No web results returned for this query.")

Sample web_search response

{
  "results": [
    {
      "title": "Example research source",
      "url": "https://example.com/research",
      "description": "A sample source for a research brief."
    }
  ],
  "query": {},
  "next_cursor": null
}

Custom MCP server

Build a custom MCP server with Brave Search

Create a hosted MCP server that combines Brave Search tools with your other connectors, Tasks and memory folders. You choose each tool it exposes, so a server can share Brave Search reads with write tools left off.

Share the server with your team, and each person adds it to the client they already use.

How permissions work Package an MCP server

How to set it up

Connect Brave Search on the qbash Connectors page.
Create an MCP server and add the Brave Search tools you want to share.
Paste the server URL into your client. It connects with OAuth or an access token.

Brave Search MCP questions

Which key does a Task use?

The Brave Search API key explicitly selected under Tools → Integrations. Endpoint access depends on its Brave plan. Saving checks format without making a provider call.

Can requests incur charges?

Yes. Brave plan activation requires a card, and successful API calls can incur usage charges. Each connector call makes one request without automatic retries.

Build a Brave Search task

Write it in Python with AI steps, or describe it to your coding agent through the qbash MCP.

Add the qbash MCP Create account