How to Connect Ringostat to ChatGPT via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Ringostat, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Ringostat + ChatGPT

Ringostat call tracking and virtual PBX: the call log with traffic sources, talk time, status, employees and recording links, who is online or in a call, employees with departments, the daily SIP online report and Smart Phone statuses. Starting a callback is installed switched off.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

RINGOSTAT_AUTH_KEY, RINGOSTAT_PROJECT_ID

Step 1 — Get credentials

Setting up takes about 2 minutes and needs a project administrator in Ringostat.

1. In Ringostat open Settings, Integrations, Ringostat API and copy the Auth-key into RINGOSTAT_AUTH_KEY. It belongs to one project and is sent as the Auth-key header.
2. Set RINGOSTAT_PROJECT_ID to the number of that project: the value after project_id= or projectId= in the address bar of the Ringostat web app, e.g. 39071. Only the employee, SIP report and custom status tools use it.
3. Install the connector; the check runs ringostat_list_online_sip.

What it reads: the call log of a period, one row per call with the columns you ask for: date, caller and called number, call type, status (disposition), talk time, total duration and waiting time, employee name and department, number pool and forwarding scheme, target and repeated flags, UTM source, medium, campaign, content and term, landing page and referrer, the reason a call was missed, CSAT rating, call id and recording link; the SIP accounts online right now and those in a call right now; the employees with SIP status, full name, e-mail, extension, staffId, departments and call directions (main and backup SIP accounts or phone numbers); online and offline time per employee and day; and the custom Smart Phone statuses such as Lunch or Meeting.

Call log: ringostat_list_calls takes from and to as YYYY-MM-DD HH:MM:SS; without them it returns the last 24 hours. The answer is one array with every call of the period, not paginated, so on busy projects the AI keeps periods short (a day or a week) and asks only for the fields it needs. Talk time is billsec in seconds; call_type is in, out, callback, transitin or transitout; proper_flag and repeated_flag mark target and repeated calls. For statistics per employee the AI groups the rows by employee_fio and sums billsec.

Filters and sorting: filters are Ringostat expressions joined by commas, e.g. call_type=in,billsec>=30, with =, <>, >, <, >=, <= or ~ (a regular expression, base64-encoded). order sorts, e.g. calldate desc; merge groups calls by caller number per day (1) or over the whole period (2).

Personal data: phone numbers and recording links are personal data. Recording links in recording and recording_wav stay available for one year.

Switched off at install: ringostat_start_callback starts a real call that connects a project number with a phone number or an employee's SIP login. It dials at once and costs call minutes, so an administrator turns it on deliberately. Even then the AI shows you both numbers and waits for your yes. Numbers are in international format without +.

Read-only POST calls: the employee list, the SIP report and the custom statuses are POST requests in Ringostat's API, but they only read.

Common errors: 401 or 403 mean a missing or wrong Auth-key, or a key and a project id from different projects. A JSON-RPC error from the employee, report or status tools usually means a wrong RINGOSTAT_PROJECT_ID; "User does not exist" means the employee filter matched nobody.

The connector does not change PBX settings, employees, number pools or forwarding schemes, and it returns recording links rather than the audio itself.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in ChatGPT

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

ChatGPT adds MCP servers as plugins on its Plugins page, on the web and on paid plans. Developer mode is no longer needed. In a Business workspace only admins and owners can add one; in Enterprise and Edu an admin can grant the Create plugins with MCPs permission.

1. Go to chatgpt.com/plugins, click Add, then Add custom MCP server.
2. Enter a name, e.g. Name: Ringostat.
3. Under Connection, enter the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID and keep Authentication on OAuth.
4. Select I understand and want to continue, then Create as a plugin. When ChatGPT asks, sign in to AnythingMCP and allow access.
5. Install the new plugin from your personal plugins, then type @ in a chat and pick it.

Available tools

Example prompts

• "How many incoming calls did we get yesterday, how many were missed, and what was the average talk time?"
• "Group last week's calls by employee with the number of calls and the total talk time."
• "Which UTM sources and campaigns brought target calls this month?"
• "Who is online right now, and which of them are on a call?"
• "How long was each employee online per day last week?"

FAQ

Does the free ChatGPT plan work with custom MCP servers? OpenAI documents custom MCP servers for paid plans only; the Free plan is not on its list.

Next steps

• Connector landing page
• Connect to Claude
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse
• Connect to Microsoft Copilot