> 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-tools/data-and-code/extract-json-data-with-jmespath.md).

# Extract JSON Data with JMESPath

Select a value or list from JSON that is already available in the workflow. Use it to pass only the fields needed by the next action.

## Extract a field

1. Pass the JSON object or array to **JSON Input**.
2. Enter **Field Path** using the structure of that input. `user.name` selects a nested name; `items[0].id` selects the first item’s ID; `[].name` selects names from a top-level list.
3. Run the tool and inspect **Output**. Check both the value and whether the result is a single item or a list.

**Result:** **Output** contains the selected value as text. Objects and lists are serialized as JSON; a missing value becomes an empty string.

## Behavior and troubleshooting

Array positions start at zero. Missing paths can return an empty result, so check that the upstream step supplied the expected structure. Use [JSON Processor](https://docs.stackai.com/stackai-tools/data-and-code/json-processor.md) when you want to read a JSON file URL or return JSON text.

## Inputs

| Field                 | Parameter    | Description                                                                             |
| --------------------- | ------------ | --------------------------------------------------------------------------------------- |
| JSON Input (required) | `json_input` | JSON data to extract from. Can be a JSON or an Array of JSON objects                    |
| Field Path (required) | `field_path` | Path to extract (e.g., 'user.name', 'items\[0].id', or '\[:].name' for all array items) |

## Outputs

| Field  | Parameter | Description                             |
| ------ | --------- | --------------------------------------- |
| Output | `output`  | The extracted data from the JSON string |

## Related guidance

[Data Types, Lists, Missing Values, and Empty Results](https://docs.stackai.com/technical-reference/workflow-execution/data-types-lists-missing-values-and-empty-results.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-tools/data-and-code/extract-json-data-with-jmespath.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.
