DeepSift Search MCP server
Commit Nov 12, 2026Performs web searches and extracts relevant text passages from websites and PDFs to provide concise answers for AI agents.
Also known as pavanmulka/deepsift, deepsift
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Nov 12, 2026
- License
- MIT
What is DeepSift Search MCP?
DeepSift Search performs web searches and extracts relevant text passages from websites and PDFs to provide concise answers for AI agents.
Summary generated from the project's README
About DeepSift Search MCP server
DeepSift Search provides a way to perform web searches and extract specific text from websites or PDFs for AI agents. It functions as a self-hosted alternative to Tavily, running locally on your laptop using an existing Claude subscription or DuckDuckGo as a backup. This setup allows you to find websites, read HTML and PDF content while stripping away ads and clutter, and select only the most relevant passages to answer a query.
Developers can use the local version with Claude Code on Mac or Linux, or opt for the hosted Apify version for team use. The hosted version uses Google and Yahoo results and requires an Apify token. It is designed to be a drop-in replacement for Tavily by supporting the same search, extract, crawl, and map request formats. While the local version relies on your personal Claude plan, the Apify version operates on a pay-per-use model without a subscription.
What you can do with it
- 1Extract specific pricing informationAsk the agent to read multiple web pages and focus specifically on finding cost details.
- 2Conduct multi-search investigationsPerform a deep research task that generates a written report with numbered sources.
- 3Map website structuresRetrieve a list of all available page addresses on a specific documentation site.
- 4Crawl entire domains for dataInstruct the tool to read many different pages from a single website to find relevant content.
Written from the project's README. Every use case is checked against a quote from it.
How to install DeepSift Search MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall DeepSift Search MCP in Claude Code
$ claude mcp add --transport http deepsift https://aadstra--deepsift-search.apify.actor/mcpInstall DeepSift Search MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"deepsift": {
"url": "https://aadstra--deepsift-search.apify.actor/mcp"
}
}
}Install DeepSift Search MCP in VS Code
.vscode/mcp.json
{
"servers": {
"deepsift": {
"type": "http",
"url": "https://aadstra--deepsift-search.apify.actor/mcp"
}
}
}Install DeepSift Search MCP in VS Code CLI
$ code --add-mcp '{"name":"deepsift","type":"http","url":"https://aadstra--deepsift-search.apify.actor/mcp"}'Install DeepSift Search MCP in Codex
$ codex mcp add deepsift --url https://aadstra--deepsift-search.apify.actor/mcpInstall DeepSift Search MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.deepsift] url = "https://aadstra--deepsift-search.apify.actor/mcp"
Install DeepSift Search MCP in Gemini CLI
$ gemini mcp add -s user --transport http deepsift https://aadstra--deepsift-search.apify.actor/mcpInstall DeepSift Search MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"deepsift": {
"url": "https://aadstra--deepsift-search.apify.actor/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablepavanmulka/deepsift is public and reachablegithub.com/pavanmulka/deepsift ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/pavanmulka/deepsift ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubDeepSift
A free, self-hosted alternative to Tavily for Claude Code. Ask one question; DeepSift searches the web, reads every page, and hands back only the paragraphs that matter. It runs on your laptop and uses the Claude subscription you already pay for.
Tavily is a paid web search API built for AI agents. You send one question; it searches the web, opens the best pages, cuts out the passages that answer the question, and sends it all back in one tidy reply. That's great, but every call costs credits.
DeepSift does the same job on your own computer, in three steps:
- Find the right websites, using Claude's web search on your existing Claude subscription (with free DuckDuckGo as a backup).
- Read every page itself: HTML and PDFs, with menus, ads and clutter stripped out.
- Pick the passages that best match your question, and give them back in one reply.
No per-call bill, no API key to buy.
Don't want to run it yourself? Use DeepSift Search on Apify
DeepSift Search is the hosted version: Google and Yahoo results, the same passage picking, nothing to install, and it works for apps and teams, not just your own laptop.
-
Tavily drop-in: same
/search,/extract,/crawland/maprequests and responses. Change one line:from tavily import TavilyClient client = TavilyClient(api_key="<YOUR_APIFY_TOKEN>", api_base_url="https://aadstra--deepsift-search.apify.actor") -
MCP server for Claude, Cursor and others:
https://aadstra--deepsift-search.apify.actor/mcpwith your Apify token as a Bearer header. -
Claude Code plugin:
/plugin marketplace add pavanmulka/deepsift, then/plugin install deepsift-search@deepsift. Claude Code asks for your Apify token once. -
Pay per use, no subscription: $4 per 1,000 searches, $1 per 1,000 pages read. Failed requests are free, and a free Apify account includes $5 of credit every month.
The Apify version lives in .actor/ and deepsift/actor.py; it never uses your Claude subscription.
What Claude Code gets
After installing, every Claude Code session has these tools:
| Tool | What you'd ask | What it does |
|---|---|---|
web_search |
"web_search Databricks Unity Catalog pricing" | One topic → many websites → the best passages from each, in one reply |
web_read |
"read these 3 pages and focus on pricing" | Full text of up to 20 pages or PDFs, or only the parts about a topic |
web_map |
"list all pages on docs.example.com" | A site's page addresses |
web_crawl |
"read the pricing pages on example.com" | Reads many pages of one site, keeps the relevant ones |
web_research |
"research the top 5 vector databases with sources" | A multi-search investigation that returns a written report with numbered sources (takes minutes) |
The same abilities work from any terminal:
deepsift search "Databricks Unity Catalog pricing" --advanced
deepsift read https://example.com/page --focus "pricing"
deepsift map https://docs.example.com
deepsift crawl https://docs.example.com --instructions "pricing"
deepsift research "Which vector databases support hybrid search?"
Install (about 1 minute)
You need a Mac or Linux computer with Claude Code and Python 3.10+.
git clone https://github.com/pavanmulka/deepsift.git
cd deepsift
./install.sh
claude auth login # only if you aren't signed in to Claude Code's command line yet
Open a new Claude Code session and ask it to use web_search. That's it.
./uninstall.sh removes it from Claude Code again.
How it compares to Tavily
| Tavily | DeepSift | |
|---|---|---|
| Cost | Pay per credit | Free (uses your Claude plan) |
| Speed per search | 1–2 s | ~10–30 s through Claude; ~1–3 s on the DuckDuckGo backup |
| Search, extract, crawl, map, research | ✓ | ✓ |
| Same request/response format | — | ✓ (optional local HTTP API, see below) |
| Runs where | Their servers | Your laptop |
Limits, honestly:
- Searches through Claude count toward your Claude plan's usage limits (3 at a time at most). Repeat searches within 24 h come from a local cache.
- DuckDuckGo pauses you after a burst of quick searches; the tool then rests it for 15 minutes.
- Pages that only show their text after JavaScript runs come back thin.
- It's meant for your own personal use with your own Claude subscription. To power an app for other people, use a proper paid API.
Optional: a local Tavily-compatible API
./run.sh starts an HTTP server on 127.0.0.1:8787 with Tavily's paths and fields (/search, /extract,
/crawl, /map, /research, GET /research/{id}, /usage). Code written for Tavily can point its base
URL there. Every reply reports usage.credits: 0.
Settings
Copy .env.example to .env to change engines, models, cache time, or set an API key for the HTTP server.
How it works
question ─► find sites (Claude WebSearch via `claude -p`, or DuckDuckGo)
─► download pages in parallel (httpx) ─► readable text (trafilatura, pypdf)
─► split into passages ─► rank by relevance to the question (BM25) ─► one reply
claude -p always runs on your subscription sign-in. ANTHROPIC_API_KEY is removed before it starts,
so it never bills an API account by accident.
Tests
.venv/bin/python -m pytest -q tests
The tests run offline, using a stand-in for claude.
License
MIT
DeepSift Search MCP questions
How do I add DeepSift Search MCP to Claude Code?
Run claude mcp add --transport http deepsift https://aadstra--deepsift-search.apify.actor/mcp in your terminal. Add --scope user to make it available in every project.
How do I add DeepSift Search MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Can I use DeepSift to power an application for other users?
The self-hosted version is intended for personal use with your own Claude subscription; for powering apps for others, you should use the hosted Apify version.
Does DeepSift support PDF files?
Yes, it can read the full text of PDFs and extract relevant parts.