> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/stackai-mcp/tool-reference/projects-and-workflow-authoring/projects-create.md).

# projects\_create

Generate a new project from a natural-language description and attempt to publish it.

**Effect:** This call saves data or changes configuration. Review the behavior below before using it.

## Inputs

| Name          | Type   | Requirement | Description                                      |
| ------------- | ------ | ----------- | ------------------------------------------------ |
| `description` | string | Required    | Description of the resource or requested change. |

## Example

These are MCP tool arguments, not an HTTP request body. Replace bracketed IDs with values returned from your account.

```json
{
  "description": "Create a text assistant that summarizes the supplied passage. Keep the source facts and mark missing information clearly. Do not add external integrations."
}
```

## Result

Abbreviated result example; unshown fields are omitted for clarity.

```json
{
  "project_id": "<project-id>",
  "project_url": "<project-url>",
  "publish_error": null,
  "unresolved_connection_provider_ids": []
}
```

## Behavior

This is not a draft-only creation tool.

Describe input, output, model behavior, knowledge sources and integrations precisely.

Inspect the returned project\_id, project\_url, publish\_error, unresolved connections and action\_param\_corrections, then read the project to confirm its published state before treating it as ready.

Generation is nondeterministic, and retrying can create another project.

## Troubleshooting

If publication fails, keep the returned project ID and repair that project. Repeating creation can produce another project. Resolve each provider listed in `unresolved_connection_provider_ids`.

## Related resources

[Projects and workflow authoring](https://docs.stackai.com/stackai-mcp/tool-reference/projects-and-workflow-authoring.md)

[Connection, permissions, pagination, and recovery](https://docs.stackai.com/stackai-mcp/best-practices-and-troubleshooting.md)


---

# 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.stackai.com/stackai-mcp/tool-reference/projects-and-workflow-authoring/projects-create.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.
