modsearch
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | 🥇 全网最强的 DeepSeek Harness 免费联网搜索插件，免费免注册免 API key。为不能联网的模型补上搜索，问网页或 X，拿回结构化 JSON 证据（搜索、抓取、引用）。
No outside reports on file
This tool exposes your AI agent to whatever unfiltered information exists on the public web, including lies and manipulation tactics, with no safety filters or verification.
Based on public adoption and transparency signals as of Oct 25, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourcenpm (@liustack/modsearch)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y @liustack/modsearchAbout Modsearch
Modsearch is a web search plugin that lets AI agents look up information on the internet and X (formerly Twitter). It returns search results and web page content as structured JSON data, designed to work with DeepSeek and other AI models that don't have built-in web access.
Who it’s for
Developers who run AI agents or chatbots that need real-time web information. It's marketed as free and requiring no API key or signup.
Alternatives
- Perplexity API: Commercial web search integration with more built-in fact-checking.
- Brave Search API: Privacy-focused search alternative that doesn't track users.
- Native model web search: Use Claude, GPT-4, or Gemini's official web search features if available for your use case.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/liustack/modsearch (opens external site) for installation and integration instructions specific to your AI platform.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 873
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Malicious search results: Websites in search results could contain false information, misleading claims, or fabricated evidence that the AI accepts as fact.
- Web page injection attacks: Malicious websites could embed hidden instructions or fake data in their HTML that tricks the AI into doing something unintended.
- Social media manipulation: X posts and user-generated content in results may contain misinformation, scams, or attempts to manipulate the AI's responses.
- Data leakage: The skill sends your search queries and potentially sensitive conversation context to external websites and may log this data.
- No built-in verification: The tool doesn't verify website authenticity or fact-check results, so it can't distinguish real news from fake sites.
How to lower the risk
Least-privilege permissions
- Only enable this skill when the AI genuinely needs to search; disable it for internal-only tasks.
- Restrict which websites the agent is allowed to visit if the tool supports URL filtering.
Network isolation
- Run the agent in a sandboxed environment so web requests can't affect other systems.
- Monitor outgoing network traffic to spot unusual search patterns or data exfiltration.
Monitoring
- Log all searches the agent performs and review them regularly for suspicious queries.
- Alert on searches for sensitive terms, competitor data, or personal information.
Red flags to watch for
- Repeated searches for the same sensitive topic or attempts to extract private data.
- Search results that contradict factual information you know to be true.
- AI responses that cite sources from sketchy or newly-registered websites.
Questions
How do I install Modsearch?
Install Modsearch with npm install @liustack/modsearch or run it directly with npx -y @liustack/modsearch. For agent integration and configuration flags, see the documentation at github.com/liustack/modsearch. Pin an exact version and pass --ignore-scripts if you want to block post-install hooks.
Are there security reports about Modsearch?
No reports found for this package in our research (last checked 2026-10-29). Modsearch currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include malicious search results, web page injection attacks, social media manipulation.
Is Modsearch actively maintained?
Modsearch has 873 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/liustack/modsearch before pinning it in production.
What are alternatives to Modsearch?
Notable alternatives to Modsearch include Perplexity API (Commercial web search integration with more built-in fact-checking), Brave Search API (Privacy-focused search alternative that doesn't track users), Native model web search (Use Claude, GPT-4, or Gemini's official web search features if available for your use case). You can also compare Modsearch side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Modsearch? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/liustack-modsearch)HTML embed:
<a href="https://agentarmorhq.com/skills/liustack-modsearch"><img src="https://agentarmorhq.com/api/badge/liustack-modsearch" alt="AgentArmorHQ Risk Grade for Modsearch" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "liustack-modsearch"Share with your security lead
Need sign-off to use modsearch? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: modsearch
- **Listing URL:** https://agentarmorhq.com/skills/liustack-modsearch
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 873 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** npm (@liustack/modsearch)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts @liustack/modsearch`
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 25, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- liustack
- Source code
- github.com/liustack/modsearch
- Install command
- npm install @liustack/modsearch
- Est. context load
- ~101 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 873 GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-25
Community
Discussions for Modsearch
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude