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

> ## Agent Instructions
> To search or read these docs, connect the Ringg docs MCP server at https://docs.ringg.ai/mcp (no key needed; tools search_ringg_ai and query_docs_filesystem_ringg_ai) instead of browsing pages one by one. Setup for each client: https://docs.ringg.ai/resources/mcp-server/docs-mcp-server/mcp-for-ai-assistants.md
> The dashboard labels agents "Assistants"; these docs say "agent". Both mean the same object, identified by agent_id.
> API base URL: https://prod-api.ringg.ai/ca/api/v0. Send the workspace API key in the X-API-KEY header, from server-side code only.
> Placing a call dials a real phone number and spends credits. Confirm the number with the user before calling.
> To act on a Ringg workspace (place calls, edit agents, read transcripts), use the separate Ringg workspace MCP server at https://mcp.ringg.ai/mcp: https://docs.ringg.ai/resources/mcp-server/workspace-mcp-server/overview.md

# Ringg AI MCP server

> Connect Claude, ChatGPT, Cursor or any MCP client to Ringg AI to place calls, read transcripts and build or edit agents from a chat with your workspace API key.

Connect the server once with your workspace [API key](/documentation/manage-account/api-key), then ask in plain language, for example "call this number with my appointment agent and tell me what they said": the client places the call, waits for it to end and reads you the transcript.

It is built on the open [Model Context Protocol](https://modelcontextprotocol.io) (MCP), so any client that supports MCP over Streamable HTTP can use it. Everything it does you can also do in the dashboard or the [API](/api-reference/introduction/authentication); MCP is for working from a chat or a coding agent.

## Server URL

```text theme={null}
https://mcp.ringg.ai/mcp
```

Transport: Streamable HTTP. How each client authenticates: [Connect an assistant](/resources/mcp-server/workspace-mcp-server/connect-an-assistant).

### Two servers, two jobs

Ringg has a second MCP server that only searches this documentation. The **MCP** entry in the menu next to **Copy page** on every docs page installs that one, not the workspace server.

| Server | URL | What it does | Needs |
| - | - | - | - |
| Ringg AI MCP server (this chapter) | `https://mcp.ringg.ai/mcp` | Acts on your workspace: places calls, edits agents, reads transcripts | Your workspace API key |
| [Docs MCP server](/resources/mcp-server/docs-mcp-server/mcp-for-ai-assistants) | `https://docs.ringg.ai/mcp` | Searches and reads these docs as Markdown (`search_ringg_ai`, `query_docs_filesystem_ringg_ai`) | Nothing; public pages only |

Connect both to a coding agent and it can read how a feature works, then do it in your workspace.

## Before you start

<Columns cols={2}>
  <Card title="A workspace API key" icon="key" href="/documentation/manage-account/api-key" horizontal>
    The owner generates it under **Settings → API key**.
  </Card>

  <Card title="A number for live calls" icon="hash" href="/documentation/inventory/phone-numbers/buy-or-import-a-number" horizontal>
    Ringg test numbers can't place live calls.
  </Card>
</Columns>

## What the client can do

| Area | Tools |
| - | - |
| Check the workspace | `get_account_overview`: agents, phone numbers, credits, last-30-day metrics and whether you are ready to call |
| Place and follow calls | `place_call`, `get_call` (can wait until the call ends, then returns transcript, recording and analysis) |
| Read history and metrics | `list_calls`, `get_call_analytics` |
| Manage agents | `list_agents`, `get_agent`, `create_agent`, `update_agent`, `list_voices` |
| Edit prompts | `edit_prompt_section`, `set_agent_prompt` |
| Manage an agent's tools | `get_agent_tools`, `upsert_api_tool`, `upsert_function_tool`, `remove_agent_tool`, `test_api_tool`, `test_jq` |
| Build multi-prompt agents | `get_flow_building_guide`, `get_flow`, `create_flow_agent`, `upsert_flow_node`, `upsert_flow_edge`, `delete_flow_node`, `delete_flow_edge`, `publish_flow`, `discard_flow_draft` |

It also offers resources such as `ringg://agents` and ready-made prompts such as `launch_first_call` ([tool reference](/resources/mcp-server/workspace-mcp-server/tool-reference)).

## Quick start

<Steps>
  <Step title="Add the connector">
    In Claude or ChatGPT, add `https://mcp.ringg.ai/mcp` as a custom connector and click **Connect**. A Ringg page opens; paste your key once. Claude Code, Cursor and scripts skip the sign-in and send the key as a bearer token. Step by step per client: [Connect an assistant](/resources/mcp-server/workspace-mcp-server/connect-an-assistant).
  </Step>

  <Step title="Ask">
    Start with "What's in my Ringg AI workspace? Am I ready to place calls?"
    <Check>The client lists your agents, numbers and credits, and suggests a first call.</Check>
  </Step>
</Steps>

<Warning>
  `place_call` dials a real phone number and spends credits. Keep your client's confirmation prompt on for it, and check the number and purpose before you approve.
</Warning>

## Example requests

* "List my voice agents and show me the full configuration of the appointment one."
* "Create an outbound agent in Hindi that tells customers their order is ready for pickup and asks whether they'll collect it today or tomorrow."
* "Call +91 98765 43210 with it, callee name Priya, order\_id 4821. Wait for the call and summarise what she said."
* "How did calling go this week? Connection rate, average duration and the most common reasons calls failed."

## Limits

* Calls follow your workspace's usual rules: DND, calling hours, [call limits](/documentation/manage-account/call-limits), credits and caller-ID availability.
* Connector tokens and registrations expire; see [what Ringg stores](/resources/mcp-server/workspace-mcp-server/security-and-faq#what-ringg-stores).
* Requests are rate-limited per client.
* Phone numbers in tool results are masked when your workspace's privacy settings require it.

## Next steps

<Columns cols={2}>
  <Card title="Connect an assistant" icon="link" href="/resources/mcp-server/workspace-mcp-server/connect-an-assistant">
    Claude, ChatGPT, Claude Code, Cursor and other MCP clients.
  </Card>

  <Card title="Tool reference" icon="wrench" href="/resources/mcp-server/workspace-mcp-server/tool-reference">
    Every tool, resource and prompt, with inputs.
  </Card>

  <Card title="Security and FAQ" icon="shield-check" href="/resources/mcp-server/workspace-mcp-server/security-and-faq">
    Sign-in, what is stored and how to revoke access.
  </Card>
</Columns>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.