Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Regression Watch run a quick regression check on agent support-bot from v1.2 to v1.3"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for Agent Update Regression Watch - run regression checks, get drift reports, compare versions.
Run regression check on agent after update.
Parameters:
agent_id (string, required): Agent identifier
from_version (string, required): Previous version
to_version (string, required): New version
test_suite (string, optional): "full", "quick", or "critical_only" (default: "full")
Get drift report for an agent over time.
Parameters:
agent_id (string, required): Agent identifier
days (integer, optional): Days of history (default: 30)
Get detailed comparison report between versions.
Parameters:
agent_id (string, required): Agent identifier
from_version (string, required): Previous version
to_version (string, required): New version
Related MCP server: deploy-check
pip install -r requirements.txtpython main.py{
"mcpServers": {
"regression-watch": {
"command": "python",
"args": ["/path/to/mcp-regression-watch/main.py"],
"cwd": "/path/to/mcp-regression-watch"
}
}
}MIT
This server cannot be deployed
Synthetic checks, nightly regression replay and model-drift alerts for AI agents
QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.
Recurring agent jobs that run on our servers and ping you only when the result changed.
Compares declared agent access against actual enforcement per identity class, with drift watch.