io.github.dockndevai/mcp-cdp MCP Server
io.github.dockndevai/mcp-cdp
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.dockndevai/mcp-cdp MCP server?
Safe-by-default MCP that drives an Electron/Chrome app over CDP: DOM, console, network, input.
How to install io.github.dockndevai/mcp-cdp
Copy-paste configuration for popular MCP clients.
CDP_PORTThe --remote-debugging-port your app/browser exposes (default 9222).
CDP_HOSTHost serving the DevTools endpoint (default 127.0.0.1; non-loopback needs CDP_ALLOW_REMOTE).
CDP_MODEAccess mode: read-only | read-write | admin. Starts read-only; interactions need read-write.
CDP_ALLOW_EVALSet true to allow the evaluate tool (arbitrary JS) — admin mode only. Default false.
CDP_TARGET_ALLOWLISTComma-separated URL patterns; interactions are confined to matching targets. Empty = all.
CDP_DRY_RUNSet true to log interactions without dispatching them to the browser.
{
"mcpServers": {
"mcp-cdp": {
"command": "npx",
"args": [
"-y",
"@dockndevai/mcp-cdp"
],
"env": {
"CDP_PORT": "<YOUR_CDP_PORT>",
"CDP_HOST": "<YOUR_CDP_HOST>",
"CDP_MODE": "<YOUR_CDP_MODE>",
"CDP_ALLOW_EVAL": "<YOUR_CDP_ALLOW_EVAL>",
"CDP_TARGET_ALLOWLIST": "<YOUR_CDP_TARGET_ALLOWLIST>",
"CDP_DRY_RUN": "<YOUR_CDP_DRY_RUN>"
}
}
}
}Related MCP servers
ClickHouse query & management for AI agents — SQL-classified read/write/destructive gating.
Debezium / Kafka Connect CDC connector management for AI agents — governed, secret-safe.

Search & edit Grafana dashboards, query datasources (PromQL/LogQL/SQL), inspect alerts.

Apache Kafka monitoring & management for AI agents (with consumer lag) — governed.
Keycloak admin for AI agents — realms, users, clients, roles; safe-by-default governance.
Kubernetes monitoring & ops for AI agents — safe-by-default access modes and guards.