Deep ResearchSAFE
An MCP (Model Context Protocol) server that enables comprehensive research capabilities for Claude
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP (Model Context Protocol) server that enables comprehensive research capabilities for Claude and other MCP-compatible AI assistants. This server integrates web and academic search functionality, allowing AI models to access current information from multiple sources, follow relevant links, and provide well-structured research results.
Overview
Claude Deep Research is a powerful research tool that extends the capabilities of LLMs by providing:
- Web search integration through DuckDuckGo
- Academic research access through Semantic Scholar
- Content extraction from web pages
- Comprehensive analysis with structured formatting
- Visualization guidance for data representation
The server follows MCP design principles to provide a seamless integration with Claude and other AI assistants.
Features
- Unified Research Tool: Single interface for web and academic information
- Multi-Source Integration: Combines information from various sources into cohesive research
- Content Extraction: Pulls relevant information from web pages
- Academic Source Discovery: Finds scholarly articles related to your topic
- Smart Formatting: Properly formats research with citations
- Visual Framework: Provides guidance for creating effective data visualizations
- Structured Analysis: Organizes research using academic methodologies
Installation
Prerequisites
- Python 3.8 or higher
- pip or uv package manager
Quick Install
# Using pip pip install mcp httpx beautifulsoup4 # Clone the repository git clone https://github.com/yourusername/claude-deep-research.git
Configuration
The server works out of the box with default settings, but you can modify the following parameters in deep_research.py for customization:
# Configuration USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome
478c46581929OBSERVED · 2026-10-07Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
deep_research | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass, no_license.
478c46581929full audit observations/trust-audit/mcp-server/mcherukara__deep-research-3.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 478c46581929 | SAFE | B | 89 | first audit |
Questions
What is the Deep Research MCP server?
An MCP (Model Context Protocol) server that enables comprehensive research capabilities for Claude
What tools does Deep Research expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Deep Research safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Deep Research need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (478c46581929), read on 2026-10-07. The repository is watched and re-audited when it changes.