> For the complete documentation index, see [llms.txt](https://docs.ngsurvey.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ngsurvey.com/ai-suite/artemis-ai-agent/mcp.md).

# MCP

You can carry out the tasks described in this section through the ngSurvey Model Context Protocol (MCP) server. Connect a compatible AI assistant to ngSurvey and ask it to work with your surveys, responses, and reports. The actions it can perform depend on the tools available through the connection and the permissions granted to it.

Through MCP, you can find existing surveys, create new ones, and translate survey content. You can organize questions into pages, add or edit questions and answer options, copy questions, and build matrices with rows and columns. You can also configure skip logic to show or hide questions based on respondents’ answers and validate answers using reusable regular expressions or custom JavaScript.

You can customize the survey’s appearance through MCP by creating themes with CSS and CSS variables or generating images for backgrounds and other visual elements. Before collecting live feedback, you can add test respondents and generate synthetic responses to preview how the results will look.

Once responses are available, you can use MCP to filter and group results and compare counts, percentages, averages, and Net Promoter Scores (NPS). For open-ended questions, you can retrieve responses, examine sentiment, and use labels or clusters to identify recurring themes. You can also investigate changes in a metric by comparing results across groups or time periods.

You can then use MCP to create a report in ngSurvey and add charts, NPS visualizations, explanatory text, and cross-tabulation tables. For example, you can compare satisfaction scores by region, examine the themes in each region’s comments, and present both findings in the same report.


---

# 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.ngsurvey.com/ai-suite/artemis-ai-agent/mcp.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.
