Skip to content

Start building

Integration · Security and identity

AI agents for Snyk

List Snyk projects and their open vulnerabilities, license and code issues by severity, see fix advice, and ignore an issue with a reason, in any Snyk region, with a Snyk API token or service account token.

Actions
10
Read
9
Write
1

Actions

What your agents can do in Snyk

10 actions. Each one is a tool your agents can call and a step your workflows can run.

Read 9

Look things up. Nothing changes.

  • List projects

    Lists an organization's projects (one per manifest, container image, code repository or IaC file scanned), with their latest issue counts.

  • Get a project

    Reads one project by ID: data.attributes (name, type, origin, status, target file and branch, created, tags, business criticality, environment, lifecycle) and data.meta.

  • List issues

    Lists an organization's issues (vulnerable packages, license problems, code and IaC findings), optionally for one project, by severity, status (open or resolved), type and whether ignored.

  • Get an issue

    Reads one issue by its ID: data.attributes with title, description, type, effective severity, status, ignored, key, problems (CVE, CWE, Snyk vulnerability IDs), coordinates.

  • List a project's vulnerabilities with fix advice

    Lists a project's vulnerability and license issues with how to fix them (Snyk V1 API), optionally by severity and type.

  • List a project's ignores

    Lists the issues ignored in a project (Snyk V1 API; ignores from .snyk files are not included), as an object keyed by Snyk issue ID.

  • List targets

    Lists an organization's targets (the repositories, images or CLI uploads that projects come from), optionally by display name or URL.

  • List organizations

    Lists the Snyk organizations the token can reach, as data: each with its id and attributes (name, slug, group_id, is_personal).

  • Check the token's user

    Reads who the token belongs to, as data: its id, type (user, service_account or app_instance) and attributes (name, username, email or default org).

Write 1

Create, change or send.

  • Ignore an issue

    Ignores a vulnerability or license issue in one project (Snyk V1 API), with a reason and a reason type.

A person can approve first

Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything.

Connection

How it connects

Connect it once in the console, then give it to the agents and workflows that need it.

API key

Paste an API key from your Snyk account.

What you enter

  • API token

Settings

  • Snyk region
  • Organization ID

Kept safe

  • Credentials are stored encrypted with your organization's own keys.
  • They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
  • Calls go only to the tool's own servers.

How we protect your data

Ideas

Ideas to start with

Starting points made only from the actions above. Mix them with any other tool your agents can use.

  • 01

    Ask about your Snyk data

    Ask a question in plain words. The agent can list projects, get a project or list issues in Snyk, then answers with what it found.

  • 02

    Share what it finds in Slack

    Give one agent Snyk and Slack: it can list projects in Snyk and post a summary to a Slack channel in the same run.

  • 03

    Run it as a workflow step

    Add "Ignore an issue" to a workflow, and it runs in Snyk the same way every time, with or without an agent.

FAQ

Snyk and MyDeepAgents

Can MyDeepAgents connect to Snyk?

Yes. The Snyk connector has 10 actions: 9 read and 1 makes changes. Your agents can call them as tools, and your workflows can run them as steps.

How do I connect Snyk?

Paste an API key from your Snyk account. You'll need: API token. The connection also asks for: Snyk region and Organization ID. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.

Can an agent change data in Snyk without asking?

Only if you let it. Its one action that changes data can be set to wait for a person's approval before it runs.

Can I use Snyk in workflows as well as agents?

Yes. Every Snyk action also works as a step in a workflow, and the same connection serves your agents and your workflows.

Early access

Put Snyk to work

Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.