AI Integration (MCP)
Crosscheck integrates with AI coding assistants through the Model Context Protocol (MCP). This allows AI tools to access your Crosscheck workspace data, helping you debug issues, analyze captures, and understand team feedback without leaving your development environment.
What is MCP?
The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources. Instead of copying and pasting information between Crosscheck and your AI assistant, MCP creates a direct connection so the AI can query your workspace data programmatically.
Compatible AI Clients
The Crosscheck MCP server works with any MCP-compatible AI client, including:
- Claude (Anthropic)
- Cursor
- Windsurf
- Other MCP-compatible tools and editors
What AI Can Do with Crosscheck
Once connected, your AI assistant can perform the following actions against your Crosscheck workspace:
| Capability | Description |
|---|---|
| Browse Projects | List all projects in your workspace to understand how captures are organized |
| Find Checks | Search and filter captures by project, type, or recency to locate specific bug reports |
| Analyze Check Details | View full check information including screenshots, metadata, and technical data |
| Debug Console Errors | Extract and analyze JavaScript errors and console logs captured with a check |
| Read Team Feedback | Access comments on checks, including video timestamps, to understand team discussions |
Setup
To connect your AI client to Crosscheck, add the MCP server URL to your client's configuration file.
Open your AI client configuration
Add the Crosscheck MCP server
mcpServers section of your configuration:{
"mcpServers": {
"crosscheck": {
"url": "https://mcp.crosscheck.cloud/mcp"
}
}
}Authenticate
Example Use Cases
Here are some example prompts you can use with your AI assistant once Crosscheck is connected:
- "Show me the most recent bug reports in the Dashboard project."
- "Find all checks with console errors from the last week."
- "Analyze the network requests in check PROJ-42 and identify any failed API calls."
- "Summarize the team comments on the latest screen recording."
- "What JavaScript errors were captured in the most recent instant replay?"
Privacy and Security
The Crosscheck MCP integration is designed with security in mind:
- Workspace-scoped — The AI client can only access data within the workspace you authorize. It cannot see data from other workspaces.
- Read-only — The MCP integration provides read-only access. Your AI assistant cannot modify, delete, or create checks or other data in Crosscheck.
- OAuth secured — All connections are authenticated through OAuth with your Crosscheck account. Access can be revoked at any time from your account settings.