# create_auth_session

Starts a browser login and returns a loginUrl plus sessionRequestId. Use as STEP 0 in a fresh conversation before any protected tool. Show the loginUrl to the user as a clickable link in their language, then poll get_auth_session until 'active' and pass session_request_id on every later call. Returns sessionRequestId, loginUrl, pollUrl and expiresIn.

Agent View of the PolicyLayer registry record for `create_auth_session`. HTML page: https://policylayer.com/tools/de-agentview-agentview-mcp/create-auth-session

## Facts

- Tool: `create_auth_session`
- Server: agentView (`https://agentview.de/mcp`) — https://policylayer.com/tools/de-agentview-agentview-mcp.md
- Homepage: https://github.com/https://agentview.de/mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 2
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `scope` | string | no | Requested access scope. Must be either 'content_only' (read and send content to displays) or 'admin' (content_only plus create/delete/rename displays). Defaults |
| `agent_identifier` | string | no | Optional display name of the MCP client or agent, shown to the user in the browser consent screen. Example: 'ChatGPT' or 'my-home-automation'. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_auth_session",
    "arguments": {}
  }
}
```

## Why create_auth_session is rated Medium

An AI agent can call create_auth_session faster than any human can review: one bad instruction and it creates or modifies resources in agentView by the hundred, each call as confident as the last.

Risk signals: Bulk/mass operation — affects multiple targets

## Use case

AI agents use create_auth_session to create or update resources in agentView, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your agentView environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches agentView:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_auth_session": {
      "limits": [
        {
          "counter": "create_auth_session_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on agentView (56)

- `delete_asset` — Destructive — https://policylayer.com/tools/de-agentview-agentview-mcp/delete-asset.md
- `delete_data_slot` — Destructive — https://policylayer.com/tools/de-agentview-agentview-mcp/delete-data-slot.md
- `delete_display` — Destructive — https://policylayer.com/tools/de-agentview-agentview-mcp/delete-display.md
- `delete_organization` — Destructive — https://policylayer.com/tools/de-agentview-agentview-mcp/delete-organization.md
- `logout` — Destructive — https://policylayer.com/tools/de-agentview-agentview-mcp/logout.md
- `remove_display_from_org` — Destructive — https://policylayer.com/tools/de-agentview-agentview-mcp/remove-display-from-org.md
- `revoke_api_key` — Destructive — https://policylayer.com/tools/de-agentview-agentview-mcp/revoke-api-key.md
- `broadcast_content` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/broadcast-content.md
- `claim_display` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/claim-display.md
- `fetch` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/fetch.md
- `get_account` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-account.md
- `get_agent_artifact` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-agent-artifact.md
- `get_asset` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-asset.md
- `get_auth_session` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-auth-session.md
- `get_data_slot` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-data-slot.md
- `get_display` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-display.md
- `get_display_preview_url` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-display-preview-url.md
- `get_license_info` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-license-info.md
- `get_organization` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-organization.md
- `get_public_status` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-public-status.md
- `get_storage_usage` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-storage-usage.md
- `get_store_template_content` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-store-template-content.md
- `get_store_template_details` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-store-template-details.md
- `get_store_template_install_options` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/get-store-template-install-options.md
- `list_api_keys` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/list-api-keys.md
- `list_assets` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/list-assets.md
- `list_data_slots` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/list-data-slots.md
- `list_display_categories` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/list-display-categories.md
- `list_displays` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/list-displays.md
- `list_organizations` — Read — https://policylayer.com/tools/de-agentview-agentview-mcp/list-organizations.md
- …and 26 more: https://policylayer.com/tools/de-agentview-agentview-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=de-agentview-agentview-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/de-agentview-agentview-mcp