@infoinlet/mcp-browser-research

Web browsing + research for AI agents: fetch & read pages, structured extraction, Exa web search & deep research. MCP server.

latest

npm

Version: 0.1.1

Version published: 2 months ago

Maintainers: 1

Created: 2 months ago

Source

browser-research

Web browsing + research for AI agents, as an MCP server. Design doc: ../../docs/05-BROWSER-RESEARCH-MCP.md.

Tools:

Tool	Needs	What
`browse_url`	—	Fetch a page → clean readable main-content text (+ optional links).
`extract_from_page`	OpenRouter	Fetch a page → structured JSON per your instruction.
`web_search`	Exa	Semantic web search (ranked results).
`deep_research`	Exa + OpenRouter	Search → read top results → synthesize a cited answer.

browse_url/extract_from_page work with no search key (only OpenRouter for extraction). web_search/deep_research return a clear "needs EXA_API_KEY" message until you set one. JS-rendered SPAs return server HTML; a Browserbase-backed render path is a documented v2 toggle.

Run

cp .env.example .env   # OPENROUTER_API_KEY (extraction) + EXA_API_KEY (search, optional)
npm install && npm run build
node dist/server.js

FAQs

What is @infoinlet/mcp-browser-research?

Is @infoinlet/mcp-browser-research well maintained?

Package last updated on 29 May 2026

Did you know?

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install