Snyk API & Web MCP Server
Connects AI coding assistants to Snyk API & Web for onboarding scan targets, configuring authentication, running DAST scans, and triaging findings through natural language.
README

Snyk API & Web MCP Server
Connect your AI coding assistant to Snyk API & Web so it can onboard scan targets, configure authentication, run DAST scans, and triage findings — all through natural language.
Built on FastMCP 2.0, works with Cursor, Claude Code, Devin, Windsurf, and any MCP-compatible client.
Naming note: Snyk API & Web was formerly known as Probely. The API endpoints (
api.probely.com), web console (plus.probely.app), and MCP tool names (probely_*) still use the legacy domain and prefix. Environment variables and config sections use the newSAW/sawnaming.
See USER_GUIDE.md for usage, examples, and tool reference.
This repository is closed to public contributions. We appreciate community interest, but we do not accept pull requests, issues, or other contributions from external contributors at this time. If you have found a security issue, please see SECURITY.md.
Requirements
- Python 3.10+
- Snyk API & Web API key
Quick Start
1. Get Your API Key
Go to https://plus.probely.app/api-keys and create an API key.
Important
Use a custom role, limited-scope API key for the Snyk API & Web MCP Server. Create the key only with the permissions required for the intended actions. Do not use a highly privileged or global API key, as this can affect your entire account and its resources.
2. Install
Windsurf Marketplace (Windsurf users)
Install directly from the Windsurf Marketplace:
- Open Windsurf and click the MCPs icon in the Cascade panel, or go to Windsurf Settings → Cascade → MCP Servers.
- Search for Snyk API & Web and click Install.
- When prompted, enter your API key.
No manual configuration needed — Windsurf handles the setup automatically.
One-command install (any MCP client)
uvx --from git+https://github.com/snyk/saw-mcp.git saw-mcp
Or add to your MCP client configuration:
{
"mcpServers": {
"SAW": {
"command": "uvx",
"args": ["--from", "git+https://github.com/snyk/saw-mcp.git", "saw-mcp"],
"env": {
"MCP_SAW_API_KEY": "your-api-key"
}
}
}
}
<details> <summary>Alternative installation methods</summary>
Install from release tarball
tar -xzvf SnykAPIWeb-<version>.tgz
cd SnykAPIWeb
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
Download from Releases and replace <version> with the actual version number (e.g., 1.0.0).
Clone from source
git clone https://github.com/snyk/saw-mcp.git
cd saw-mcp
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
</details>
3. Store Your API Key
The server reads your API key from (in order of precedence): environment variable MCP_SAW_API_KEY → .env file → config/config.yaml.
Option A: Environment variable (recommended for Marketplace / uvx installs)
export MCP_SAW_API_KEY="your-api-key"
Option B: .env file (recommended for source installs)
Run the setup script (prompts securely, no key in shell history):
./scripts/setup-env.sh
Or pipe from a secret manager: op read 'op://vault/item/key' | ./scripts/setup-env.sh
This writes a .env file in the project root (gitignored). The server loads it automatically at startup.
4. Configure Your IDE
If you installed from the Windsurf Marketplace, configuration is automatic. For other clients, add to your MCP client configuration:
{
"mcpServers": {
"SAW": {
"command": "uvx",
"args": ["--from", "git+https://github.com/snyk/saw-mcp.git", "saw-mcp"],
"env": {
"MCP_SAW_API_KEY": "your-api-key"
}
}
}
}
For host-specific setup see the Installation Guides.
<details> <summary>Additional configuration options</summary>
- Override the base URL: add
"MCP_SAW_BASE_URL": "https://your-instance-url"to theenvblock. - Use a config file: set
"MCP_SAW_CONFIG_PATH": "/path/to/config.yaml"instead. - Set log level: add
"MCP_SAW_LOG_LEVEL": "DEBUG"(options: DEBUG, INFO, WARNING, ERROR, CRITICAL; default: INFO).
</details>
5. Start Using
Ask your AI assistant to:
- "Configure a Snyk API & Web API target from this OpenAPI schema / Swagger document / Postman collection."
- "Configure a Snyk API & Web web target for this authenticated application."
See prompts.md for a full catalog of example prompts — from simple one-liners to complex multi-target workflows.
IDE Integration
Detailed per-host guides live in docs/installation-guides/:
| Host | Guide |
|---|---|
| Cursor | install-cursor.md |
| Windsurf | install-windsurf.md |
| Claude Desktop | install-claude.md |
| Devin / Other IDEs | install-devin.md |
Packaging
bash scripts/package.sh
Creates dist/SnykAPIWeb-<version>.tgz (version from snyk_apiweb/__init__.py).
Development & Testing
Run the Server (standalone)
Running the server directly starts it and waits for an MCP client connection. This is mainly useful for development and debugging:
./venv/bin/python -m snyk_apiweb.server
Development Mode (hot reload)
For active development with automatic reload on file changes:
./scripts/dev.sh
License
This project is licensed under the Apache License 2.0.
<!-- mcp-name: io.github.snyk/saw-mcp -->
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。