Web search (Brave) and SSRF-safe page fetching, extraction and comparison for agents
Mcp-web-research is an MCP integration. Web search (Brave) and SSRF-safe page fetching, extraction and comparison for agents.
The published npm package is @opafex/mcp-web-research, version 0.1.0. Its declared MCP transport is stdio.
The package declares BRAVE_SEARCH_API_KEY: Brave Search API key; enables web_search and research_topic (recommended); WEB_RESEARCH_SEARCH_PROVIDER: Search provider: "brave" or "duckduckgo" (unofficial HTML scraper, explicit opt-in only); USER_AGENT: User-Agent sent with every request (default identifies the bot and links to the repo); SEARCH_CACHE_TTL: Search result cache TTL in seconds (default: 900); PAGE_CACHE_TTL: Fetched page cache TTL in seconds (default: 3600); FETCH_TIMEOUT_MS: Per-request timeout in milliseconds, across all redirect hops (default: 10000); MAX_HTML_SIZE: Maximum bytes read from a page body (default: 1000000).
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository. This profile uses version 0.1.0 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related developer tools MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| BRAVE_SEARCH_API_KEY | Brave Search API key; enables web_search and research_topic (recommended) | Check documentation |
| WEB_RESEARCH_SEARCH_PROVIDER | Search provider: "brave" or "duckduckgo" (unofficial HTML scraper, explicit opt-in only) | Check documentation |
| USER_AGENT | User-Agent sent with every request (default identifies the bot and links to the repo) | Check documentation |
| SEARCH_CACHE_TTL | Search result cache TTL in seconds (default: 900) | Check documentation |
| PAGE_CACHE_TTL | Fetched page cache TTL in seconds (default: 3600) | Check documentation |
| FETCH_TIMEOUT_MS | Per-request timeout in milliseconds, across all redirect hops (default: 10000) | Check documentation |
| MAX_HTML_SIZE | Maximum bytes read from a page body (default: 1000000) | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Sign up at [semanticapi.dev](https://semanticapi.dev) to get your API key.
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and
FastMCP server exposing Joplin notes, notebooks, tags, and imports.
Async deep research MCP server for AI agents and MCP clients with Brave, GitHub, Context7, and SQLite-backed local storage.