SourceWeave Web Search MCP Server
Search-first MCP server and CLI for web research. Overview • Getting started • Managed local runtime • MCP client setup • CLI • Container deployments • OpenWebUI • Runtime configuration • Development
People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.
VERIFIED ACTIVE
LAST COMMIT 2026-04-23 · ★ 2 · #56 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25
MIT · Python servers · how we verify → /methodology
01 · Install SourceWeave Web Search
before you install - you'll need
Set SOURCEWEAVE_SEARCH_SEARXNG_BASE_URL, SOURCEWEAVE_SEARCH_CRAWL4AI_BASE_URL, SOURCEWEAVE_SEARCH_CACHE_REDIS_URL before connecting.
Claude Code
claude mcp add mrnaqa-sourceweave-web-search -- uvx sourceweave-web-search Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"mrnaqa-sourceweave-web-search": {
"command": "uvx",
"args": [
"sourceweave-web-search"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license MIT - declared in the repository
pypi package sourceweave-web-search - check the name against the project README before installing (PyPI has no namespace ownership)
registry namespace io.github.MRNAQA is GitHub-verified and matches the repo owner
03 · What SourceWeave Web Search can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
v0.5.0 · 2026-04-23
Unreleased · 0.5.0 · add a managed local runtime to sourceweave-search-mcp so the MCP server can discover, reuse, or start its Docker-backed dependencies automatically when explicit endpoint variables are absent…
v0.4.0 · 2026-04-21
0.4.0 · add effort guidance to search_web so MCP clients can choose quick, normal, or deep research passes with matching search depth and pagination · emit richer search status updates while fetching and refining…
v0.3.0 · 2026-04-15
simplify the implementation back to the minimal public search/read behavior after reviewing the hidden internal feature paths with a KISS/YAGNI lens · keep the default fit_markdown-first cleaned output path and compact…
04 · Who maintains SourceWeave Web Search
SourceWeave Web Search is maintained by mrnaqa. It's the only MCP server we track from this author; the repo dates to Apr 2026.
05 · Facts
- repository
- github.com/mrnaqa/sourceweave-web-search
- category
- web scraping - ranked #56 of 78 actively-maintained web scraping servers as of 2026-08-25.
- registry
- io.github.MRNAQA/sourceweave-web-search (active, first published 2026-04-13 · 5 versions)
- packages
- pypi:sourceweave-web-search
06 · SourceWeave Web Search FAQ
What is SourceWeave Web Search?
Search-first MCP server and CLI for web research. Overview • Getting started • Managed local runtime • MCP client setup • CLI • Container deployments • OpenWebUI • Runtime configuration • Development
Is SourceWeave Web Search still maintained?
Yes - as of 2026-08-25, its last commit was 2026-04-23. We re-verify nightly.
How do I install SourceWeave Web Search?
Run `uvx sourceweave-web-search`. The README documents 3 environment variables (SOURCEWEAVE_SEARCH_SEARXNG_BASE_URL, SOURCEWEAVE_SEARCH_CRAWL4AI_BASE_URL, SOURCEWEAVE_SEARCH_CACHE_REDIS_URL) to set first. Set SOURCEWEAVE_SEARCH_SEARXNG_BASE_URL, SOURCEWEAVE_SEARCH_CRAWL4AI_BASE_URL, SOURCEWEAVE_SEARCH_CACHE_REDIS_URL before connecting. You can also paste the ready-made client config above.
Does SourceWeave Web Search run locally?
Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to SourceWeave Web Search
Alternatives to SourceWeave Web Search
Maintained web scraping servers if SourceWeave Web Search isn't the fit.
- Firecrawl MCP Server MCP server for Firecrawl - web search, scraping, and biomedical/arXiv paper search. ★ 7,310 · 2026-08-25
- Exa Fast, intelligent web search and web crawling. New mcp tool: Exa-code is a context tool for coding ★ 4,917 · 2026-08-21
- Apify MCP Server Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡ ★ 4,718 · 2026-08-23
- Wigolo Local-first web intelligence MCP server for AI coding agents ★ 4,647 · 2026-08-24
- Tavily MCP MCP server for advanced web search using Tavily ★ 2,351 · 2026-08-20
- Open Brand Extract brand assets (logos, colors, backdrop images, brand name) from any website URL ★ 785 · 2026-05-12
Pairs well with
Servers that cover what SourceWeave Web Search doesn't - only shown when the pairing reason fits the companion.
- SearXNG Search → search companion search · ★ 1,158
- Blockrun MCP → search companion search · ★ 388
- Supabase → database companion database · ★ 2,871
- MongoDB MCP Server → database companion database · ★ 1,106
- Codebase Memory → memory companion memory · ★ 40,198
- Memorix → memory companion memory · ★ 688
More web scraping MCP servers · Wet MCP · Getregdata · Proxy4agents MCP · Octen MCP · Scraper
More Python MCP servers · Gsc Indexer MCP · Agent Bom · Allure Testops MCP · GitLab CI MCP · Package Version Check MCP · see all