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 -->
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.