LabscoMCP early access ↗
reading-plus-aiMCP SERVER

Deep Research by Reading Plus AI

A structured research workflow, delivered as one prompt: elaborate the question, split it into subquestions, search, and write a cited report.

by reading-plus-ai ↗Reasoning Scaffolds & Agent Workflow EnginesCommunity

LABSCO SUMMARY

The value is the sequence, not a search API.

It brings no data source of its own - the searching is the client's. What it adds is structure: forcing the question to be decomposed before searching, and the sources to be cited in the write-up. That is what separates a research report from a summary of the first five results.

What it is

A prompt-shaped server rather than a tool-shaped one. It ships a single deep-research prompt that walks a research question through a fixed sequence, using the client's own web search to gather sources.

What you get

  • Question elaboration - the scope, the key terms and what is actually being asked
  • Subquestions generated to cover the different aspects of the topic systematically
  • A targeted search per subquestion, using the client's built-in web search
  • Findings synthesised across sources, with citations kept attached
  • A structured report produced as an artifact, with evidence-based conclusions rather than a link dump

Requirements

uv and Python 3.10+. The README's uvx line names a package that is not on PyPI, so run it from a clone: uv sync, then the README's own development config, uv --directory <YOUR_PATH_TO_MCP_SERVER_DEEP_RESEARCH> run mcp-server-deep-research. No API key of its own - the searching is done by the client, so it needs a client whose own web search is available. In use you select the deep-research prompt and give it a question.

Setup effort

Build from source — git clone https://github.com/reading-plus-ai/mcp-server-deep-research

See installation options