web-forager
A search-and-fetch toolkit for AI agents — MCP server and standalone Agent Skills powered by DuckDuckGo and Jina Reader
Decision gist · record as of 2026-08-14
Yes, if you need web search and page fetching for AI agents. The package is actively maintained, has low install friction, carries a permissive MIT license, and integrates cleanly with MCP clients like Claude Desktop. No known vulnerabilities. The main gotcha is Python version support (3.10–3.13 only) and potential rate-limiting or API stability issues with DuckDuckGo and Jina Reader, which the fact sheet does not detail.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or higher; Python 3.14 is not yet supported.
- Low install friction with a pure Python wheel.
- Requires Python 3.10 or higher.
License · maintenance · safety
MIT (permissive) — MIT license is permissive, allowing use in commercial and private projects with minimal restrictions — only requiring attribution.
last release 2026-03-05 (162 days) · last repo commit 2026-08-09 · 10 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 328,912 downloads/mo, #7,551 on PyPI
Alternatives
Verify before relying
pip install web-forager
# CLI usage
web-forager search "your query" --max-results 5
web-forager news "your query" --max-results 10
web-forager fetch "https://example.com" --format markdown
# Or start as MCP server
web-forager serve- Whether Jina Reader API access requires authentication or has rate limits.
- DuckDuckGo API stability and any terms-of-service constraints for automated queries.
- Performance characteristics when handling large result sets or long-form page content.
What it is and what it does
Web Forager is a search-and-fetch toolkit designed for AI agents and LLM workflows. It wraps DuckDuckGo web search, DuckDuckGo news search, and Jina Reader into a unified interface that can run as an MCP server (for integration with Claude, Cursor, and other MCP clients) or as standalone command-line tools and Python Agent Skills. The package converts web pages and search results into markdown or JSON formats optimized for LLM consumption, handling the common friction points of web scraping — cookie banners, dynamic content, and inconsistent HTML structure — by falling back through multiple fetching strategies.
The toolkit ships with six runtime dependencies: mcp and fastmcp for MCP server functionality, requests and urllib3 for HTTP transport, beautifulsoup4 for HTML parsing, and ddgs for DuckDuckGo integration. It supports Python 3.10 through 3.13 and is actively maintained. The package is positioned as a research and fact-checking aid for AI agents, with specialized Agent Skills for competitive analysis and technology evaluation.
Use it for
- Integrate web search into Claude Desktop or Cursor via MCP to give LLMs real-time web access.
- Build autonomous research agents that fetch and summarize news articles and web pages.
- Fact-check claims by searching DuckDuckGo and converting results into structured data for LLM analysis.
- Monitor competitive products and technologies by automating news search and page fetching.
- Use standalone Agent Skills in Python scripts for specialized research workflows without MCP overhead.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need web search and page fetching for AI agents.
The package is actively maintained, has low install friction, carries a permissive MIT license, and integrates cleanly with MCP clients like Claude Desktop. No known vulnerabilities. The main gotcha is Python version support (3.10–3.13 only) and potential rate-limiting or API stability issues with DuckDuckGo and Jina Reader, which the fact sheet does not detail.
Install
web-forager on PyPI
Before you install
Low install friction with a pure Python wheel. Requires Python 3.10 or higher. Actively maintained with a recent commit on 2026-08-09 and six runtime dependencies (mcp, fastmcp, requests, urllib3, beautifulsoup4, ddgs) that are themselves well-established.
Requires Python 3.10 or higher; Python 3.14 is not yet supported.
License in practice
MIT license is permissive, allowing use in commercial and private projects with minimal restrictions — only requiring attribution.
Quickstart
pip install web-forager
# CLI usage
web-forager search "your query" --max-results 5
web-forager news "your query" --max-results 10
web-forager fetch "https://example.com" --format markdown
# Or start as MCP server
web-forager serveVerify before relying
- Whether Jina Reader API access requires authentication or has rate limits.
- DuckDuckGo API stability and any terms-of-service constraints for automated queries.
- Performance characteristics when handling large result sets or long-form page content.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 6 packagesmcpfastmcprequestsurllib3beautifulsoup4ddgs |
| Maintenance | Actively maintained 162 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 328,912 / month, #7,551 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 3 - AlphaIntended Audience :: DevelopersProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Topic :: Internet :: WWW/HTTP :: Indexing/SearchTopic :: Software Development :: Libraries :: Python Modules |
Evidence: web_forager-3.0.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “web search for ai agents”
- web-foragerWeb Forager is a search-and-fetch toolkit for AI agents that…
- strands-agents-toolsProvides ready-to-use tools for AI agents to perform file operations,…
- valyuValyu provides a Python SDK for accessing web search, content…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also duckduckgo-mcp · duckduckgo-mcp-server · duckduckgo-search · mcp-server-fetch · cognee · ddgs · gpt-researcher · arxiv-mcp-server · reme-ai · wikipedia-mcp