AgentArmorHQ
Sign in

openserp

MCP server · GitHub · ★ 1.5k · graded 2026-10-26Source linked

Self-hosted web search for AI agents and SEO. Google, Bing, Yandex, Baidu, DuckDuckGo & Ecosia, rendered in a real browser: ranked results and clean page Markdown. API, CLI, MCP 🎉

No outside reports on file

The main danger is trusting web content retrieved from the open internet—attackers can create convincing fake information or inject hidden commands into pages that confuse your AI agent.

Based on public adoption and transparency signals as of Oct 26, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Openserp helpful?

What it can access

  • Local filesReads local filesNOTED
  • Command executionNo shell command runner notedLOW
  • Network reachFetches arbitrary web URLsREVIEW
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (karust/openserp)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/karust/openserp ↗

All setup options ↓

Check this skillWatch it in my stackCompareAdd to allowlistREADME badgeView project

About Openserp

OpenSerp lets AI agents search the web across multiple search engines (Google, Bing, Yandex, Baidu, DuckDuckGo, Ecosia) and get results as clean Markdown text. It runs on your own server instead of relying on external APIs, and can render pages in a real browser to show ranked results and formatted content.

Who it’s for

Developers building AI agents that need web search abilities, and teams wanting to self-host search functionality without depending on third-party APIs. It's useful for SEO tools and applications that need fresh web data.

Alternatives

  • Tavily API: Commercial web search API designed for AI agents with safety features
  • Perplexity API: Hosted search engine API with built-in citation and ranking
  • SerpAPI: Third-party search API for Google, Bing, and other engines
  • Searxng: Open-source metasearch engine you can self-host

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README. The tool can be set up as an MCP server for Claude Desktop, CLI tool, or API service depending on your needs. Check the GitHub repository for detailed installation and configuration instructions for your specific use case.

Why this grade

CC — Moderate risk signals

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

35/100
GitHub stars
1.5k
Listing last refreshed
2026-10-28

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).

Check a specific version →

Risks to watch for

  • Search manipulation: Attackers can create web pages with misleading content that ranks high, which the agent will retrieve and trust
  • Prompt injection in results: Web pages can contain hidden instructions that confuse or redirect the AI agent's behavior
  • Credential exposure: The server needs network access to external search engines and your own data; logs might contain sensitive search queries
  • Browser rendering attacks: Malicious JavaScript on pages could be executed by the real-browser rendering feature, potentially leaking data
  • Rate limiting: Heavy use could trigger blocks from search engines or expose your server's IP address

How to lower the risk

Least-privilege permissions

  • Run the MCP server with minimal OS permissions and network access
  • Restrict which search engines and sites the agent can query

Network isolation

  • Keep the server on a private network or behind authentication if possible
  • Monitor outbound traffic to detect unusual search patterns or data exfiltration

Monitoring

  • Log all search queries and results for audit trails
  • Review agent responses to spot if web content is steering behavior unexpectedly

Red flags to watch for

  • Sudden changes in agent responses after searches
  • Repeated queries to suspicious or newly-created domains
  • Unusual amounts of traffic or rate-limiting warnings

Questions

How do I install Openserp?

Openserp does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/karust/openserp.

Are there security reports about Openserp?

No reports found for this package in our research (last checked 2026-10-29). Openserp currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include search manipulation, prompt injection in results, credential exposure.

Is Openserp actively maintained?

Openserp has 1.5k GitHub stars. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/karust/openserp before pinning it in production.

What are alternatives to Openserp?

Notable alternatives to Openserp include Tavily API (Commercial web search API designed for AI agents with review features), Perplexity API (Hosted search engine API with built-in citation and ranking), SerpAPI (Third-party search API for Google, Bing, and other engines), Searxng (Open-source metasearch engine you can self-host). You can also compare Openserp side by side with other MCP servers in the Related tools section on this page.

README badge and team notes

Maintain or use Openserp? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Openserp

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Openserp](https://agentarmorhq.com/api/badge/karust-openserp)](https://agentarmorhq.com/skills/karust-openserp)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/karust-openserp"><img src="https://agentarmorhq.com/api/badge/karust-openserp" alt="AgentArmorHQ Risk Grade for Openserp" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "karust-openserp"

Share with your security lead

Need sign-off to use openserp? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: openserp
- **Listing URL:** https://agentarmorhq.com/skills/karust-openserp
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.5k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** Reads local files
- **Command execution:** No shell command runner noted
- **Network reach:** Fetches arbitrary web URLs
- **Credentials:** No API token required
- **Package source:** GitHub (karust/openserp)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/karust/openserp
- **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 26, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
karust
Source code
github.com/karust/openserp
Est. context load
~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
Popularity
1.5k GitHub stars
Last updated
2026-10-28
Last graded
2026-10-26

Community

Discussions for Openserp

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.

Was this listing for Openserp helpful?

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