Open Deep Search

MCPOpen SourceMIT22.2

by tositon • Search & Retrieval

An open-source MCP server that performs structured, iterative deep research using Brave Search and the Sequential Thinking approach to produce well-sourced reports.

Example Use Cases

1
Perform comprehensive, multi-step research on complex topics and produce citation-backed reports.
2
Integrate browser/search-based research capability into MCP-enabled assistants like Claude Desktop or Cursor.
3
Run iterative searches and analyses (Sequential Thinking) and test interactions via MCP Inspector or publish tools on Smithery.

Description

Open Deep Search breaks complex questions into sub-questions, runs iterative Brave Search queries, analyzes results, and synthesizes findings into coherent, citation-backed research reports. It integrates with MCP clients (Claude Desktop, Cursor) and supports WebSocket integration for tools like Smithery and MCP Inspector. The tool is designed for reproducible, transparent research workflows with emphasis on multiple searches, result analysis, and final synthesis.

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D44/100

4/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelUnknown

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownertositon

CategorySearch & Retrieval

DependenciesStandalone