> 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-run.md).

# projects\_run

Run a published project and return its output.

**Effect:** This call executes a workflow or evaluator. Review its effects and possible usage charges before calling it.

## Inputs

| Name         | Type    | Requirement | Description                                                                                                  |
| ------------ | ------- | ----------- | ------------------------------------------------------------------------------------------------------------ |
| `project_id` | string  | Required    | ID returned by `projects_list`; use a project in the active organization.                                    |
| `inputs`     | object  | Required    | Object keyed by actual project input IDs. Text values are strings; document/image values are arrays of URLs. |
| `version`    | integer | Optional    | Published version number; omit to use the selected published version.                                        |
| `verbose`    | boolean | Optional    | Default `false`. Include expanded details. See behavior below for the scope of expansion.                    |

## Example

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

This example assumes a text input whose actual ID is `in-0`. Replace the key with the project’s input ID.

```json
{
  "project_id": "<project-id>",
  "inputs": {
    "in-0": "Summarize the supplied information."
  }
}
```

## Result

Abbreviated result example; unshown fields are omitted for clarity.

```json
{
  "output_text": "<generated-answer>",
  "project_url": "<project-url>",
  "result": {
    "outputs": {
      "out-0": "<generated-answer>"
    }
  }
}
```

## Behavior

Use actual input IDs from `projects_get`, not display names. Text inputs take strings; document and image inputs take URL arrays.

The optional integer `version` selects a published version. Omit it to use the published version selected by the service.

Read `output_text` for a text response and `result` for the full run payload. Save any run identifier returned there; use `runs_list` to locate the run when needed.

Each call creates a new run and can invoke the workflow’s external integrations.

## Troubleshooting

For `invalid_run_inputs`, inspect `allowed_keys`, `unknown_keys`, and `missing_required`. On timeout, inspect the project run history before running again; the first run may have completed.

## Related resources

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

[Inspect and run a published project](https://docs.stackai.com/stackai-mcp/workflow-recipes/inspect-and-run-a-published-project.md)

[Upload a larger document](https://docs.stackai.com/stackai-mcp/workflow-recipes/upload-a-larger-document.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-run.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.
