> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agnost.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agnost AI in Codex, Claude, and Cursor

> Integrate Agnost AI and query your dashboard from Codex, Claude Desktop, Cursor, and any MCP client

Agnost AI runs a hosted, OAuth-protected MCP server at **`https://mcp.agnost.ai/mcp`**. Add it to any MCP-aware client and ask natural-language questions about conversations, events, tool calls, intents, and violations.

## Connect

### Codex

```bash theme={null}
codex mcp add agnost-ai --url https://mcp.agnost.ai/mcp
codex mcp login agnost-ai
```

### Claude Desktop / Cursor

```json theme={null}
{
  "mcpServers": {
    "agnost-ai": {
      "url": "https://mcp.agnost.ai/mcp"
    }
  }
}
```

No API keys, no copy-pasted tokens. The first time you call a tool, the client opens a browser tab, you sign in with Google through the Agnost AI dashboard, and the tab closes. First-time users automatically receive a free organization, so the integration tool can use its organization ID without asking for it.

### Other MCP clients

Anything that speaks streamable-HTTP MCP and supports OAuth 2.1 dynamic client registration works the same way. The server publishes its OAuth metadata at:

```
https://mcp.agnost.ai/.well-known/oauth-authorization-server
https://mcp.agnost.ai/.well-known/oauth-protected-resource
```

Both discovery documents advertise the supported `agnost` OAuth scope so clients can request the server's current access level without guessing. Organization membership and permissions are still derived from the signed-in Agnost AI account.

## What you can ask

* "Which tools are failing most often this week?"
* "Show me recent conversations where users had to repeat their request."
* "Show me today's violations."
* "Summarize the top intents in this org."
* "Integrate Agnost analytics into this project."
* "Give Agnost feedback: make exports easier to automate."

When you ask to integrate Agnost, the MCP server returns the public Agnost skill installation command and a project prompt containing your authenticated default organization ID. Coding clients with terminal access can run the command and continue the integration from your project root. The response ends with a link to [open the Agnost dashboard](https://app.agnost.ai).

The feedback tool accepts anything you want to share, including something you did not like, something that felt confusing, or an idea that could make Agnost better.

## Verify

After adding the server to your MCP client, call any Agnost AI tool. The client should open a browser for OAuth the first time, then return dashboard data after login.

## Troubleshooting

* Confirm the MCP client supports streamable-HTTP MCP and OAuth 2.1 dynamic client registration.
* If OAuth does not open, remove the server from the client config and add it again.
* If a query returns no data, confirm you are logged into the right Agnost AI organization in the dashboard.

## Next steps

* [Conversations](/using-conversations): understand the interaction data you can query.
* [Intents](/using-intents): learn how user goals are represented.
* [Violations](/using-violations): learn how expected behavior is evaluated.