> For the complete documentation index, see [llms.txt](https://docs.snyk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.snyk.io/agent-security/evo-by-snyk/platform-surfaces/evo-mcp-server/common-use-cases.md).

# Common use cases

Example multi-step workflows that combine the Evo MCP server with other MCP servers to build dashboards, raise tickets, and create policies

{% hint style="info" %}
You configure any non-Snyk MCP server mentioned in this article in your own client. Snyk does not provide or support those servers, and the steps that use them depend on the permissions you grant.
{% endhint %}

The Evo MCP server runs in the same agent session as other connected MCP servers. With the right integration, you can turn an answer from Evo into a dashboard, a ticket, or a policy.

Each use case lists the prompts to send in order, and the result you get.

## Visualize the estate

{% hint style="info" %}
Requires the Evo MCP server and a client that can build dashboards, artifacts, or documents.
{% endhint %}

Produce a reporting pack for the estate:

1. "How many AI assets do we have, broken down by type and by source?" This establishes scope: models, agents, MCP servers, skills, repositories, and machines.
2. "Group our models by vendor and by country of origin."
3. "Break our models down by license type."
4. "List all open violations grouped by policy and severity."
5. "Build me a dashboard from this, with a chart for each section."

The result is a dashboard built from live Tenant data that you can regenerate on demand.

## Turn a violation into a ticket

{% hint style="info" %}
Requires the Evo MCP server and a ticketing MCP server, such as Jira, connected in the same client.
{% endhint %}

Create tickets for policy violations:

1. "Show me the open violations for this policy, with the affected asset and where it was found."
2. "Group them by repository so we raise one ticket per team rather than one per violation."
3. "Create a Jira ticket for each group in this project, with the asset list and the remediation notes in the description."
4. "Give me the ticket details so I can reference them."

The result is a set of tickets in your own tracker, populated from live violation data.

## Create a policy from estate data

{% hint style="info" %}
Requires the Evo MCP server, a Tenant role with Evo write access, and a client that supports MCP elicitation. For details, visit [Available tools](/agent-security/evo-by-snyk/platform-surfaces/evo-mcp-server.md#available-tools).
{% endhint %}

Create a policy based on risks in your estate:

1. "How many skills in our estate score 500 or above for insecure credential handling?"
2. "Show me those skills ordered by that score, with the machines they are on."
3. "Create a policy that assigns High severity to skills scoring 500 or above for insecure credential handling."
4. "Show me the violations generated by this policy."

The result is a policy tuned against the estate it governs.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.snyk.io/agent-security/evo-by-snyk/platform-surfaces/evo-mcp-server/common-use-cases.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.