Is Aguara safe to use?

Aguara has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under Apache-2.0.

How do I install Aguara?

Aguara supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What AI clients work with Aguara?

Aguara is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is Aguara actively maintained?

Aguara is actively maintained — last commit was 0 days ago. It has 81 GitHub stars.

Aguara

Name: Aguara
Author: garagon

caches · by garagon

Security scanner for AI agent skills and MCP servers. Static analysis, incident response, no LLM. One binary. Detection engine behind oktsec.

81 13/wk 0 tools GitHub npm PyPI

No known CVEs

Apache-2.0 license

Actively maintained

Last commit 0d ago

Works with most clients

Transport: stdio, sse, http

0 tools

Grade F

Edit this pageView history

Security

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "aguara": {
      "args": [
        "-y",
        "caches"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/aguara)](https://mcppedia.org/s/aguara)

Read me

What Aguara does

Security scanner for AI agent skills and MCP servers. Detect prompt injection, data exfiltration, and supply-chain attacks before they reach production.

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

60/100across 5 weighted dimensions

How we score →

0255075100

−40

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked caches against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Aguara safe to use?: Aguara has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under Apache-2.0.
How do I install Aguara?: Aguara supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with Aguara?: Aguara is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Aguara actively maintained?: Aguara is actively maintained — last commit was 0 days ago. It has 81 GitHub stars.

Similar servers

Others in security

View all →

Evil Mcp Server93

An evil MCP server used for redteam testing

30 1

io.github.jasonxkensei/xproof92

Proof primitive for AI agents on MultiversX. Anchor file hashes on-chain as verifiable proofs.

1 1

Ida Pro Mcp92

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

9.0k 3

Nothumanallowed91

Security-first platform for AI agents. 38 specialized agents, 15 AI-powered extensions, zero-knowledge multi-agent orchestration. SENTINEL WAF, Ed25519 auth, 2.6M grounding facts.

97 5

MCP Security Weekly

Get CVE alerts and security updates for Aguara and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

Security

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "aguara": {
      "args": [
        "-y",
        "caches"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/aguara)](https://mcppedia.org/s/aguara)

Read me

What Aguara does

Security scanner for AI agent skills and MCP servers. Detect prompt injection, data exfiltration, and supply-chain attacks before they reach production.

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

README

Aguara

Security scanner for AI agents and software supply chains.
Aguara checks the trust points modern projects rely on: dependencies, lockfiles, install scripts, CI workflows, MCP configs, and AI agent tools.

Installation • Quick Start • What Aguara Checks • Supply-Chain Check • AI Agent & MCP Security • CI Integration • Rules • Contributing

https://github.com/user-attachments/assets/851333be-048f-48fa-aaf3-f8cc1d4aa594

Local-first. No SaaS account. No telemetry. No LLM calls. Signed releases.

Why Aguara?

Supply-chain attacks are not just vulnerabilities in your code. They often arrive through something your project is about to trust: a dependency version, an install script, a lockfile entry, a CI workflow, or an agent tool.

Security reviews used to focus mostly on application code. Modern projects also depend on package registries, lockfiles, install scripts, CI workflows, MCP servers, and AI agent tools. Recent supply-chain incidents have shown the pattern: a legitimate package publishes a malicious version, a project installs it, and the attacker gets a chance to steal tokens, cloud credentials, CI secrets, or local files.

Aguara gives teams a local check before they trust those inputs:

before running npm install, pnpm install, or yarn install (Aguara reads package-lock.json, pnpm-lock.yaml, and yarn.lock directly, no install needed)
before letting CI execute install-time scripts
before accepting a new MCP server config
before letting an agent use a third-party skill or tool
before uploading findings to a code-scanning dashboard

For dependencies, Aguara reads resolved lockfiles where it has parsers (today this is pnpm-lock.yaml, package-lock.json, yarn.lock classic, plus Go / Rust / PHP / Ruby / Java / .NET lockfiles) and installed package trees otherwise. So a freshly cloned npm, pnpm, or yarn project can be checked before any install runs. Yarn Berry (v2+) lockfiles are the next-layer parser, not shipping today.

Installation

Homebrew (macOS/Linux)

brew install garagon/tap/aguara

Docker

docker run --rm -v "$PWD:/repo:ro" ghcr.io/garagon/aguara:0.22.0 check /repo

The image is multi-arch (linux/amd64 and linux/arm64), runs as non-root UID 10001, base images are digest-pinned, and the image is signed at the digest with Cosign plus SPDX SBOM and SLSA proven

... View full README on GitHub

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

60/100across 5 weighted dimensions

How we score →

0255075100

−40

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked caches against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Aguara safe to use?: Aguara has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under Apache-2.0.
How do I install Aguara?: Aguara supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with Aguara?: Aguara is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Aguara actively maintained?: Aguara is actively maintained — last commit was 0 days ago. It has 81 GitHub stars.

Similar servers

Others in security

View all →

Evil Mcp Server93

An evil MCP server used for redteam testing

30 1

io.github.jasonxkensei/xproof92

Proof primitive for AI agents on MultiversX. Anchor file hashes on-chain as verifiable proofs.

1 1

Ida Pro Mcp92

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

9.0k 3

Nothumanallowed91

Security-first platform for AI agents. 38 specialized agents, 15 AI-powered extensions, zero-knowledge multi-agent orchestration. SENTINEL WAF, Ed25519 auth, 2.6M grounding facts.

97 5

MCP Security Weekly

Get CVE alerts and security updates for Aguara and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?