Skip to content
Merged
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
85 changes: 44 additions & 41 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,50 @@ Agent Scan helps you keep an inventory of all your installed agent components (h
>
> By default, Agent Scan requires explicit user consent (y/n) before starting each stdio MCP server during interactive runs. This gives you control over what gets executed on your system.

## Quick Start

Choose one of two ways to run Agent Scan:

1. **Run the Python package with `uvx`** using the instructions below.
2. **Download a standalone binary** for your platform from [GitHub Releases](https://github.com/snyk/agent-scan/releases). Releases also include the SBOM, checksums, signed checksums, and source code archives.

Before using either option:

1. **Sign up at [Snyk](https://snyk.io)** and get an API token from [https://app.snyk.io/account](https://app.snyk.io/account) (API Token → KEY → click to show).
2. **Set the token as an environment variable** before running any scan:
```bash
export SNYK_TOKEN=your-api-token-here
```

### Run with `uvx`

Have [uv](https://docs.astral.sh/uv/getting-started/installation/) installed on your system, then run a full scan of your machine (auto-discovers agents, MCP servers, and skills):

```bash
uvx snyk-agent-scan@latest
```

This will scan for security vulnerabilities in MCP servers, tools, prompts, and resources. It will automatically discover a variety of agent configurations, including Claude Code/Desktop, Cursor, Gemini CLI, and Windsurf.

You can also scan particular MCP configuration files or skills:

```bash
# scan a specific mcp configuration
uvx snyk-agent-scan@latest ~/.vscode/mcp.json
# scan a single agent skill
uvx snyk-agent-scan@latest ~/path/to/my/SKILL.md
# scan all claude skills
uvx snyk-agent-scan@latest ~/.claude/skills
```

### Download a standalone binary

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shall we call it Run with standalone binary just to be consistent with the wording?


Download the binary for your operating system and architecture from the [latest GitHub Release](https://github.com/snyk/agent-scan/releases/latest). The release page also provides an SBOM (`sbom-<version>.json`), checksum files, and GitHub-generated source code archives. See [Verifying Standalone Binaries](#verifying-standalone-binaries) to verify your download.
Comment thread
SH4DY marked this conversation as resolved.

### Example Run

[![Agent Scan security vulnerabilities demo](demo.svg)](https://asciinema.org/a/716858)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This image is only for uvx so shall we call it Example uvx Run?

Then would be nice to also provide a screenshot for the Example Binary Run.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I feel like we shouldn't add more bloat to the main README, it's already too long.


## Highlights

- Auto-discover MCP configurations, agent tools, skills
Expand Down Expand Up @@ -110,47 +154,6 @@ Legend: **✓** detected · **✗** the agent supports this but Agent Scan does

‡ Amp stores project/workspace skills at `.agents/skills` (and the `.claude/skills` compatibility path); only the user-scope `~/.config/agents/skills` is detected today, so project-scope skills are supported but not yet scanned.

## Quick Start

To get started:

1. **Sign up at [Snyk](https://snyk.io)** and get an API token from [https://app.snyk.io/account](https://app.snyk.io/account) (API Token → KEY → click to show).
2. **Set the token as an environment variable** before running any scan:
```bash
export SNYK_TOKEN=your-api-token-here
```
3. Have [uv](https://docs.astral.sh/uv/getting-started/installation/) installed on your system.

### Scanning

To run a full scan of your machine (auto-discovers agents, MCP servers, skills), run:

```bash
uvx snyk-agent-scan@latest
```


This will scan for security vulnerabilities in MCP servers, tools, prompts, and resources. It will automatically discover a variety of agent configurations, including Claude Code/Desktop, Cursor, Gemini CLI, and Windsurf.

```bash
uvx snyk-agent-scan@latest
```

You can also scan particular MCP configuration files or skills:

```bash
# scan a specific mcp configuration
uvx snyk-agent-scan@latest ~/.vscode/mcp.json
# scan a single agent skill
uvx snyk-agent-scan@latest ~/path/to/my/SKILL.md
# scan all claude skills
uvx snyk-agent-scan@latest ~/.claude/skills
```

#### Example Run

[![Agent Scan security vulnerabilities demo](demo.svg)](https://asciinema.org/a/716858)

## Verifying Standalone Binaries

We use GPG signing on the release checksums file to ensure distribution integrity and authenticity.
Expand Down
Loading