Searchts MCP Server

The missing layer between AI and the web. A Python CLI and library that lets an AI agent read and search the internet, fronted by a fully open-source "unlocker" that gets through common bot-walls with no paid proxy and no API key. 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 2026-08-24 · ★ 2 · #28 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Searchts

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add capad-xyz-searchts -- uvx searchts

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "capad-xyz-searchts": {
      "command": "uvx",
      "args": [
        "searchts"
      ]
    }
  }
}

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 searchts - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.capad-xyz is GitHub-verified and matches the repo owner

03 · What Searchts can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.7.2 · 2026-08-04

0.7.2 (2026-08-04) · Fixed · capture full Grok share ids and read Perplexity Pages · add a manual dispatch path so automated tags can still publish · bump python-dotenv from 1.2.1 to 1.2.2 · bump requests from 2.32.5…

v0.7.1 · 2026-08-04

0.7.1 (2026-08-04) · Fixed · cap the SDK below 2.0, which breaks the server on startup · read ChatGPT /s/ shares and stop soft walls swallowing --human · halve CI runs, cache pip, scope token, add dependabot · automate…

v0.7.0 · 2026-07-30

credit #21 and #23 in the 0.6.0 notes · republish server.json to the MCP registry on tag push · add CDN challenge phrase matrix · explain scorecard results · carry response headers · detect Cloudflare challenges…

04 · Who maintains Searchts

searchts is maintained by capad-xyz. It's the only MCP server we track from this author; the repo dates to Jun 2026.

05 · Facts

repository: github.com/capad-xyz/searchts
website: https://github.com/capad-xyz/searchts
category: web scraping - ranked #28 of 78 actively-maintained web scraping servers as of 2026-08-25.
release cadence: 10+ releases in the last 90 days (latest 2026-08-04)
registry: io.github.capad-xyz/searchts (active, first published 2026-07-07 · 5 versions)
packages: pypi:searchts

06 · Searchts FAQ

What is Searchts?

Is Searchts still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-24 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install Searchts?

Run `uvx searchts`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does Searchts 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 Searchts

Alternatives to Searchts

Maintained web scraping servers if Searchts isn't the fit.

Pairs well with

Servers that cover what Searchts doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Amazon Scraper API · Jobseek · Crawleo MCP · Trentina · Decodo MCP Server

More Python MCP servers · Leadenrich MCP · Oh My Cassette · Nyc Property Intel · Futuristic Risk Intelligence · Hypermnesia MCP · see all