Ragstack MCP Server
Serverless document and media processing with AI chat. Scale-to-zero architecture - no vector database fees, no idle costs. Upload documents, images, video, and audio - extract text with OCR or transcription - query using Amazon Bedrock or your AI assistant via MCP. It runs locally over stdio via the published package.
People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.
VERIFIED ACTIVE
LAST COMMIT 2026-08-20 · ★ 25 · #26 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25
Apache-2.0 · Python servers · how we verify → /methodology
01 · Install Ragstack
before you install - you'll need
Set RAGSTACK_GRAPHQL_ENDPOINT, RAGSTACK_API_KEY before connecting.
Claude Code
claude mcp add hatmanstack-ragstack-lambda -- uvx ragstack-mcp Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"hatmanstack-ragstack-lambda": {
"command": "uvx",
"args": [
"ragstack-mcp"
]
}
}
} 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 Apache-2.0 - declared in the repository
pypi package ragstack-mcp - check the name against the project README before installing (PyPI has no namespace ownership)
registry namespace io.github.HatmanStack is GitHub-verified and matches the repo owner
03 · What Ragstack can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
v2.5.1 · 2026-04-27
[2.5.1] - 2026-03-28 · Fixed · KB retrieval failures silently swallowed: except Exception: pass around Bedrock KB retrieval in query_kb/handler.py hid all errors. Now surfaces ClientError with specific handling for…
v2.5.0 · 2026-03-20
[2.5.0] - 2026-03-20 · Chat API is now async (mutation + polling): queryKnowledgeBase moved from Query to Mutation. Returns immediately with PENDING status. Clients must poll getConversation for results. The old…
v2.4.0 · 2026-03-20
[2.4.0] - 2026-03-20 · Added · DLQ replay Lambda: New dlq_replay Lambda replays messages from any of the 5 DLQ/source-queue pairs (processing, batch, scrape-discovery, scrape-processing, sync). Manually triggered. FIFO…
04 · Who maintains Ragstack
ragstack is maintained by hatmanstack. It's the only MCP server we track from this author; the repo dates to Oct 2025.
05 · Facts
- repository
- github.com/hatmanstack/ragstack-lambda
- category
- web scraping - ranked #26 of 78 actively-maintained web scraping servers as of 2026-08-25.
- registry
- io.github.HatmanStack/ragstack (active, first published 2026-02-06)
- packages
- pypi:ragstack-mcp
06 · Ragstack FAQ
What is Ragstack?
Serverless document and media processing with AI chat. Scale-to-zero architecture - no vector database fees, no idle costs. Upload documents, images, video, and audio - extract text with OCR or transcription - query using Amazon Bedrock or your AI assistant via MCP. It runs locally over stdio via the published package.
Is Ragstack still maintained?
Yes - as of 2026-08-25, its last commit was 2026-08-20. We re-verify nightly.
How do I install Ragstack?
Run `uvx ragstack-mcp`. The README documents 2 environment variables (RAGSTACK_GRAPHQL_ENDPOINT, RAGSTACK_API_KEY) to set first. Set RAGSTACK_GRAPHQL_ENDPOINT, RAGSTACK_API_KEY before connecting. You can also paste the ready-made client config above.
Does Ragstack 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 Ragstack
Alternatives to Ragstack
Maintained web scraping servers if Ragstack 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 Ragstack 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 · Web Search · Seo Audit Console · Websharp · LLM Optimizer · twscrape Twitter/X (read-only)
More Python MCP servers · Bde Score · Computer-Use Agents API · Agent Magnet · Google Sheets MCP · see all