Skip to main content
Glama

How to connect Riverside to Claude Code, ChatGPT and any AI agent

Yes, Claude, ChatGPT and other AI agents can work in your Riverside account. Riverside has official apps in ChatGPT and Claude for searching, editing, clipping and publishing videos. Cotlet.dev connects your own signed-in Riverside account to any AI agent, so you can ask in plain words and the AI creates studios and schedules recording sessions for you.

What you can ask

Create a studio called "Founders Talk" and schedule a recording with Maria Lopez on Thursday at 10 am.

Schedule next week's episode for Tuesday at 3 pm and send the guest invite to james@brightlane.co.

Set up a new studio for our team podcast and book a session every Monday at 9 am for the next 4 weeks.

Move Friday's 2 pm session with Dr. Patel to Monday at 11 am and let her know.

List all sessions scheduled this month across my studios, with guest names and times.

Related MCP server: OutcomeCI MCP Server

Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.

Claude Code

claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"

ChatGPT

Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.

Cursor

Copy .cursor/mcp.json from this repo into your project:

{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}

Run it locally (stdio)

This repo is a real MCP server. It speaks MCP over stdio, lists its Riverside tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.

{"mcpServers":{"riverside":{"command":"uvx","args":["riverside-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

docker build -t riverside-mcp .
docker run -i --rm -e COTLET_API_KEY riverside-mcp

Tools: riverside_guide, riverside_status, riverside_open, riverside_read, riverside_click, riverside_type, riverside_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".

Command line

Python 3.10+, nothing else to install. From PyPI:

pip install riverside-mcp        # or run it once: uvx riverside-mcp connect
riverside-mcp connect

Or straight from this repo:

export COTLET_API_KEY="your-key"
python3 riverside_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 riverside_agent.py status    # is Riverside ready in your Cotlet.dev account
python3 riverside_agent.py guide     # Riverside screens and sign-in link
python3 riverside_agent.py read      # open Riverside, read the page, close the browser
python3 riverside_agent.py tools     # list Cotlet.dev tools
python3 riverside_agent.py serve     # start the stdio MCP server (same as no argument)

Questions from Riverside users

Does Riverside have an API?

Riverside has a Business API for select Business accounts only, with a key from your customer success manager, and it mostly gets or deletes recordings and lists scheduled events (checked 11 Oct 2026). Its official MCP server (beta, Grow, Webinar and Business plans) searches, edits and posts clips, but cannot schedule sessions or invite guests. Cotlet.dev works in your own signed-in Riverside account, so your AI agent can create studios and schedule recordings with no API key and no code.

How do I connect Riverside to ChatGPT?

Riverside has an official app in the ChatGPT directory for editing and publishing. To also create studios and schedule sessions, add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to Riverside once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no Riverside API key.

Is there a way to use Claude with Riverside?

Yes. Claude lists an Anthropic verified Riverside connector for editing, clipping and publishing. With Cotlet.dev, run the one-line claude mcp add command above in Claude Code, or add https://cotlet.dev/mcp/v1 as a custom connector in the Claude app. Claude then works in your own Riverside account.

Is there a Riverside MCP server?

Riverside has official integrations listed in ChatGPT and Claude. Cotlet.dev is a hosted MCP server that works in your Riverside account for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.

Find it on

Also works with


More: https://cotlet.dev/integrations/riverside-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=riverside

Start free: https://cotlet.dev/signup?app=riverside&utm_source=github&utm_medium=readme&utm_campaign=riverside

Available Tools

7 tools
riverside_clickBInspect

Click a numbered element on the current Riverside page.

Inputs: element (required).

riverside_closeAInspect

Close the Riverside browser session when the work is done, so credits stop running.

Inputs: no named parameters.

riverside_guideAInspect

How to work in Riverside (create studios and schedule recordings): its screens and the sign-in link. Call this first.

Inputs: task.

riverside_openAInspect

Open a Riverside page in your signed-in Cloud Browser (default https://riverside.com) to work with create studios and schedule recordings.

Inputs: url.

riverside_readAInspect

Read the current Riverside page: its text and numbered buttons, links and fields.

Inputs: element.

riverside_statusAInspect

Check that your Cotlet.dev account and Riverside are ready: account, credits and Riverside connection.

Inputs: no named parameters.

riverside_typeBInspect

Type text into a numbered field on the current Riverside page.

Inputs: text (required), element (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: open/close manage the browser session, read/click/type operate on the current page, and guide/status cover onboarding versus readiness checks. There is no meaningful overlap between page interaction, session lifecycle, and account checks.

    Naming Consistency4/5

    All tools use a consistent riverside_ snake_case prefix, making them easy to group and recognize. The only minor deviation is that guide and status are noun-like names while the other tools use verbs, but the pattern remains predictable.

    Tool Count5/5

    Seven tools is well-scoped for a browser-automation server: five core browser primitives plus two setup/guidance tools. No tool feels redundant or conspicuously missing from the set.

    Completeness4/5

    The surface covers the essential lifecycle: check readiness, open the browser, read the page, click and type, then close the session. It may lack explicit wait/navigation/keyboard primitives, but these are minor gaps for the stated Riverside studio and scheduling workflows.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      A
      maintenance
      Enables AI agents to drive your real, logged-in Chrome browser with existing sessions and cookies, bypassing CAPTCHA and anti-bot measures, with support for multi-session and human-in-the-loop workflows.
      40
      61
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to create, validate, and manage agent-powered workflows across team tools, with tools for inspecting schemas, configuring triggers, and reviewing runs and logs. It provides authorized remote access through OAuth without local installation or shared API keys.
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to drive your own signed-in ChatGPT web account — asking questions, continuing chats, attaching files, toggling thinking or web search, creating images, transcribing recordings of any length, reading replies aloud, and managing conversations, memories and projects. It runs against a local Chrome tab on chatgpt.com and reports live progress and step-named errors back to the client.
      2
      MIT