A maximum fault-tolerant, stealth-enabled MCP server for web searching and fetching.
Project description
SearchFetch (MCP Server)
A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.
Features
- Stealth Engine: Powered by CloakBrowser C++ patches +
humanizelogic. The browser renders and moves like a real user, reducing bot-detection scores. - Fault Tolerance: Auto-healing browser sessions, grace-period timeouts for SPAs, and network-level blocking of tracking scripts and media.
- Token-Optimized Output: Strips base64 images, SVGs, scripts, and inline styles from the DOM before Markdown conversion.
- Dual Runtime: Natively supports zero-install execution via both Python (
uvx) and Node.js (npx). - Template-Driven Extraction: Structured extraction via shared JSON templates (GitHub, npm, PyPI, crates.io, docs pages, Docker Hub, and more). Supports custom inline templates.
Usage & Installation
You do not need to install this repository manually. Configure your agent to use the zero-install commands npx or uvx.
Claude Desktop Configuration
Option A: Python (uvx - Recommended)
{
"mcpServers": {
"searchfetch": {
"command": "uvx",
"args": ["searchfetch"]
}
}
}
Option B: Node.js (npx)
{
"mcpServers": {
"searchfetch": {
"command": "npx",
"args": ["-y", "searchfetch"]
}
}
}
Cursor / IDE Configuration
Add via the MCP panel in Cursor settings:
- Type:
command - Command:
uvx searchfetch(ornpx -y searchfetch)
Available Tools
1. websearch
Search the web through the template pipeline. DuckDuckGo and Google are built-in; custom search templates can be selected by name.
| Parameter | Type | Default | Description |
|---|---|---|---|
query |
string | required | The search query string. |
engine |
string | "duckduckgo" |
"duckduckgo", "google", or a custom search template name. |
max_results |
number | 10 |
Maximum number of results to return. |
region |
string/null | null |
Region/language code (e.g. "us-en", "de-de"). DDG maps directly; Google maps to gl/hl. |
safe_search |
boolean/null | null |
Enable safe search. null uses the template default. |
block_media |
boolean | true |
Block images, media, and fonts at the network layer. |
2. webfetch
Fetch a page with the stealth browser and extract structured Markdown using a template. Falls back to generic Markdown extraction for unknown pages.
| Parameter | Type | Default | Description |
|---|---|---|---|
url |
string | required | Full URL (must start with http/https). |
template |
string | "auto" |
"auto", a built-in name, or inline JSON template. |
start_index |
number | 0 |
Character offset for pagination. |
max_length |
number | 10000 |
Maximum characters per request. |
block_media |
boolean | true |
Block images, videos, and fonts at the network layer. |
Template extraction supports text, markdown, attribute, and html formats; nested children; repeated sections; URL-decoding transforms; per-template cookies; and per-template resource blocking.
Built-in templates live in templates/*.json and are shared by the Node.js and Python implementations.
Local Development
# Install dependencies
npm install
pip install -e ".[dev]"
# Run tests
npm test # runs all tests (JS + Python)
npm run test:js # Node.js unit tests (built-in test runner)
npm run test:py # Python unit tests (pytest)
# Lint
npm run lint # runs all linters
npm run lint:js # ESLint
npm run lint:py # Ruff
# Format
npm run format # auto-format all source files
npm run format:check # check formatting without changes
# MCP inspector (for manual testing)
npm run inspector-js # test with MCP Inspector (Node.js)
npm run inspector-py # test with MCP Inspector (Python)
Architecture
This repository uses a flat dual-manifest structure (package.json and pyproject.toml in the root). Both runtimes (index.js for Node, server.py for Python) share the same templates/*.json files and maintain feature parity.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file searchfetch-3.2.1.tar.gz.
File metadata
- Download URL: searchfetch-3.2.1.tar.gz
- Upload date:
- Size: 17.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d4588590a55819e8c3475e4fd7499c3ec465be29ea932ad18f3c23b23c8051aa
|
|
| MD5 |
dea82cbce7e8577a771492bbcebd9d80
|
|
| BLAKE2b-256 |
e8fe234e8eee2efb6f83752858a43d0ad58fdc4bf0a4fadffdfa1328c651dacb
|
Provenance
The following attestation bundles were made for searchfetch-3.2.1.tar.gz:
Publisher:
publish.yml on maxylev/searchfetch
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
searchfetch-3.2.1.tar.gz -
Subject digest:
d4588590a55819e8c3475e4fd7499c3ec465be29ea932ad18f3c23b23c8051aa - Sigstore transparency entry: 2025710266
- Sigstore integration time:
-
Permalink:
maxylev/searchfetch@2cd728cb4a8f7106fef285c4c15fa3bf30a55cdf -
Branch / Tag:
- Owner: https://github.com/maxylev
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@2cd728cb4a8f7106fef285c4c15fa3bf30a55cdf -
Trigger Event:
release
-
Statement type:
File details
Details for the file searchfetch-3.2.1-py3-none-any.whl.
File metadata
- Download URL: searchfetch-3.2.1-py3-none-any.whl
- Upload date:
- Size: 21.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
585cb079b6c7d0e1d3313eb34a67665b996ff378554a2334f1006eeb7c3f18ad
|
|
| MD5 |
a12cc4e66dc16e3eff365357c83d61c9
|
|
| BLAKE2b-256 |
581a5036b0d5b73cd574470e75c7355c5464706cedc7241e94f75d386ef8898d
|
Provenance
The following attestation bundles were made for searchfetch-3.2.1-py3-none-any.whl:
Publisher:
publish.yml on maxylev/searchfetch
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
searchfetch-3.2.1-py3-none-any.whl -
Subject digest:
585cb079b6c7d0e1d3313eb34a67665b996ff378554a2334f1006eeb7c3f18ad - Sigstore transparency entry: 2025710400
- Sigstore integration time:
-
Permalink:
maxylev/searchfetch@2cd728cb4a8f7106fef285c4c15fa3bf30a55cdf -
Branch / Tag:
- Owner: https://github.com/maxylev
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@2cd728cb4a8f7106fef285c4c15fa3bf30a55cdf -
Trigger Event:
release
-
Statement type: