MCP Tools DirectoryAbout this integration
Web search, clean page reading & one-call research dossiers for AI agents. No API key.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.0.2
- Package
- deep-research-mcp-server
- Last compatibility test
- Not independently tested
Connect your agent
deep-research-mcp-serverPublisher README and executable manifest were reviewed from pinned captures. Public metasearch availability and site automation policies can affect results; the package, target sites, and hosted actor were not executed or independently security-audited.
Capabilities: Web search, Web page extraction to Markdown, Multi-source research dossiers
Connected profiles
Additional details
io.github.Perufitlife/deep-research-mcp-server
Source ↗ · Checked 2026-09-171.0.2
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17deep-research-mcp-server
Source ↗ · Checked 2026-09-191.0.2
Source ↗ · Checked 2026-09-19The publisher documents local search and page reading through a configured npx stdio process, using public SearXNG with a DuckDuckGo fallback; failed source fetches are skipped and reported.
Source ↗ · Checked 2026-09-19No OpenAI, Perplexity, or Tavily API key is required for the documented local search and page-reading workflow.
Source ↗ · Checked 2026-09-19Configure an MCP client to run npx with -y and deep-research-mcp-server over stdio.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19