# About the Textual A2A agent

The Textual A2A agent provides access to Tonic Textual sensitivity detection and redaction as a built-in [A2A protocol](https://a2a-protocol.org/) agent.

## Available tasks

External orchestrators, LLM frameworks, and agent marketplaces that speak A2A can:

* Detect sensitive values in a provided text string.
* Redact sensitive values in a provided text string or file.

## Supported A2A protocol versions

Textual supports the following versions of the A2A protocol:

* v0.3
* v1.0

## Getting the A2A agent card

To get the Textual A2A agent card, call `GET /.well-known/agent-card.json`.

The agent card includes:

<table><thead><tr><th width="248.24609375" valign="top">Field</th><th valign="top">Value</th></tr></thead><tbody><tr><td valign="top">Agent</td><td valign="top"><code>Textual</code>, v1.0.0, provider <code>Tonic.ai</code></td></tr><tr><td valign="top">Interface</td><td valign="top"><p>JSON-RPC at <code>https://&#x3C;host>/a2a</code></p><p>REST at <code>https://&#x3C;host>/a2a/v1/*</code></p></td></tr><tr><td valign="top">Skills</td><td valign="top"><code>pii-detect</code>, <code>pii-redact</code>, <code>file-redact</code></td></tr><tr><td valign="top">Input modes</td><td valign="top"><code>text/plain</code>, <code>application/json</code>, <code>application/pdf</code></td></tr><tr><td valign="top">Output modes</td><td valign="top"><code>application/json</code>, <code>text/plain</code></td></tr><tr><td valign="top">Capabilities</td><td valign="top">Streaming, push notifications</td></tr><tr><td valign="top">Security</td><td valign="top">OAuth2 authorization-code flow that points to the instance's built-in token endpoints.</td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.tonic.ai/textual/textual-integrations/textual-a2a-agent/about-the-textual-a2a-agent.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.