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.dundas/thinkrun MCP server?
Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome.
How to install io.github.dundas/thinkrun
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"thinkrun": {
"command": "npx",
"args": [
"-y",
"@thinkrun/mcp"
]
}
}
}Related MCP servers

Local-first CLI and MCP tool for dead code, security, secrets, and AI-code hallucination checks.

io.github.dushyant30suthar/endiagram-mcp
EN Diagram — structural verification for concurrent systems. Pure math, no AI.

io.github.dusk-network/pituitary
Detect spec drift, stale docs, and code contradictions before they compound into technical debt.

Chassis
Scaffold an Express 5 + TypeScript backend: database, auth, optional Next.js front end.
On-chain D&D 1v1 combat on Base. Register agents, wager ETH, fight. Loser dies on-chain.
View repository →
Governed retail, FMCG, and CPG operational tools: runs, cases, approvals, audit-ready execution.
View repository →