OpenReplay Connector for AI agents.
5 live capabilities
Analyze web application user sessions and technical logs.
Waiting for input…
Why people use OpenReplay
OpenReplay for Web Application Debugging
With this Connector, you just tell your AI agent what you need. It finds the project, locates the user, and pulls the session data or console logs directly into your chat. You get the technical context you need instantly, letting you focus on the fix instead of the hunt.
What Vinkius changes
You get session data and technical logs in your chat window instead of a separate dashboard.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Linking a support ticket to a session
A user reports a broken checkout.
- Real-world use case 02
Debugging console errors
You see a spike in errors.
- Real-world use case 03
Analyzing a new feature launch
You want to see how people use a new feature.
Complete set · 5capabilities
The complete OpenReplay capability set.
These are the exact actions your AI can choose when you ask it to work with OpenReplay.
01—03
3 capabilities in this set.
Part of 5 available through OpenReplay.
- 01 Capability
Get session
Retrieve metadata for a single session. This helps you get a quick summary of a user's activity.
- 02 Capability
List projects
List all projects associated with your account. Use this to see which environments are available for inspection.
- 03 Capability
List sessions
Retrieve a list of sessions for a specific project. You can filter these by User ID to find specific journeys.
04—05
2 capabilities in this set.
Part of 5 available through OpenReplay.
- 04 Capability
Search users
Find users identified within a project. Use this to correlate support tickets with actual session recordings.
- 05 Capability
List session events
Retrieve all technical and user events recorded during a session. This lets you see all clicks and console logs.
Set up in minutes
One URL. Then ask OpenReplay to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use OpenReplay from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_wnk1KautKpY80U2mk7obCeYB3o5isdyqsTp6s29d/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it OpenReplay, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable OpenReplay for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_wnk1KautKpY80U2mk7obCeYB3o5isdyqsTp6s29d/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the OpenReplay URL.
- Step 03
Save and start
Save the connection and enable OpenReplay in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"openreplay": {
"url": "https://edge.vinkius.com/vk_preview_wnk1KautKpY80U2mk7obCeYB3o5isdyqsTp6s29d/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using OpenReplay
Open Agent mode in chat and ask: "Using OpenReplay, help me...". 5 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"openreplay": {
"url": "https://edge.vinkius.com/vk_preview_wnk1KautKpY80U2mk7obCeYB3o5isdyqsTp6s29d/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using OpenReplay
Ask Copilot: "Using OpenReplay, help me...". 5 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"openreplay": {
"url": "https://edge.vinkius.com/vk_preview_wnk1KautKpY80U2mk7obCeYB3o5isdyqsTp6s29d/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using OpenReplay
Open Cascade and ask: "Using OpenReplay, help me...". 5 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"openreplay": {
"url": "https://edge.vinkius.com/vk_preview_wnk1KautKpY80U2mk7obCeYB3o5isdyqsTp6s29d/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using OpenReplay
Ask Cline: "Using OpenReplay, help me...". 5 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add openreplay --transport http "https://edge.vinkius.com/vk_preview_wnk1KautKpY80U2mk7obCeYB3o5isdyqsTp6s29d/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using OpenReplay
Ask Claude: "Using OpenReplay, show me...". 5 tools are ready
Where the request belongs
Work OpenReplay can move forward.
This is for support engineers tired of chasing ghost bugs, developers who need to see real console logs, and product managers who want to see how people actually use new features.
Support Engineer
You use this to instantly pull up a user's session recording when they report a bug, cutting out the back-and-forth with the dev team.
Frontend Developer
You use this to grab console logs and clickstreams from a failed session to reproduce a bug without having to ask the user for screenshots.
Product Manager
You use this to see how users are actually navigating a new feature by pulling session data for specific projects.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsFullStory
Manage digital experience intelligence, track users, and retrieve session data via AI agents with FullStory.
Howuku
Analyze user behavior via Howuku. track projects, recordings, and heatmaps.
Microsoft Clarity
See exactly how users interact with your website through heatmaps, session recordings, and behavioral analytics that reveal UX insights.
BugSnag
Monitor application errors via BugSnag. track stability, inspect error groups, and retrieve event details directly from any AI agent.
PostHog
Manage product analytics and feature flags via PostHog. query events, inspect cohorts, toggle flags and create annotations from any AI agent.
Rollbar
Connect your AI assistant to Rollbar to identify active bugs, review stack traces, trace code deployments, and manage error lifecycles without leaving the chat.
Bring your own AI
Change the model, client or framework. Keep OpenReplay connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about OpenReplay.
The practical details behind the request, access and result.
How can I use OpenReplay MCP to find specific user bugs?
You can ask your agent to search for a user by their email or ID. It will find the correct user profile and then pull up their recent sessions so you can see exactly what they did before the bug happened.
Can OpenReplay MCP show me console logs from a web session?
Yes, it can pull all technical events including console logs, clicks, and inputs. This makes it easy to see the exact errors a user encountered without having to ask them for screenshots.
How do I link a support ticket to an OpenReplay session?
Just give your AI agent the user's email or ID from the ticket. The Connector will find the matching user in your project and list their recent sessions for you to review.
Can I use OpenReplay MCP to see where users get stuck?
Yes, you can pull session data for specific projects or users. This helps you see where users are clicking or where they are dropping off in a specific journey, like a sign-up flow.
Does OpenReplay MCP work with my current AI client?
Yes, it works with any MCP-compatible client like Claude, Cursor, or Windsurf. Once you connect it through Vinkius, your agent can access your OpenReplay data directly.
Can I see technical logs and console errors for a specific session?
Yes! Use the list_session_events capability with a Session ID. It will retrieve all recorded technical and user events, including clicks, inputs, and console logs.
How do I find sessions for a specific user email?
First, use search_users with the email and Project ID to find the user. Then, use list_sessions with that User ID to see all their recorded activity.
Does this integration support self-hosted OpenReplay instances?
Yes. You can provide an optional OPENREPLAY_BASE_URL during setup to point the agent to your private instance instead of the default cloud API.
One connection away
Give your agent a direct line to OpenReplay.
Connect OpenReplay once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available