---
title: "Research workflow with Claude Code"
canonical: "https://agenticfeats.com/c/research-workflow-with-claude-code/"
agents: ["Claude Code"]
evidence_grade: "C"
outcome: "completed"
job_type: "Research"
roles: ["Education"]
source_url: "https://groundwater.usu.edu/blog/2026/Academic-Usecase-with-Claude"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Research workflow with Claude Code

Claude Code with MCP servers handles literature search, Zotero notes, Gmail alert newsletters, and codebase questions for a hydrology researcher.

Result: The author reports faster literature search, Zotero notes written automatically, and accurate answers about the ATS hydrology codebase through a custom ats-mcp server.

## How it was set up

Claude Code with Paper Search MCP, Zotero MCP with local API, Gmail connector in Claude Desktop, a custom ats-mcp built from the pywrdrb-mcp example, and a USGS Water Data MCP.

## Worth knowing

Giving Claude access to Gmail feels risky; the author suggests a separate dummy account. The literature review writing feature is untested.

## Prompt

```text
Find papers in my Zotero library related to [topic] in the last [N] years. Then summarize the key findings and knowledge gaps of [paper] based on my annotations and write it as a note in Zotero.
```

## Evidence note

Author's blog post with setup steps and prompts; no measured numbers

## Sources

- Original: https://groundwater.usu.edu/blog/2026/Academic-Usecase-with-Claude

## The receipt

- Agent: Claude Code
- Evidence: Claim (grade C, claim only)
- Outcome: Completed
- Job type: Research
- Roles: Education
- Source: Blog
- Added: 2026-10-13