Skip to main content

MCP Servers

The Model Context Protocol (MCP) extends CLI agents with specialized capabilities—code research, web grounding, browser automation. While IDE-based assistants (Cursor, Windsurf) often include these features built-in, CLI agents (Claude Code, Copilot CLI, Aider) rely on MCP servers to add functionality beyond basic file operations.

These MCP servers address the critical gaps in AI-assisted development workflows.

Code Research​

ChunkHound​

ChunkHound provides semantic code search and structured sub-agent research for large codebases.

What it does:

  • Multi-hop semantic search through code relationships
  • Hybrid semantic + symbol search (conceptual discovery, then exhaustive regex)
  • Map-reduce synthesis with architectural relationships and file:line citations

When to use it:

  • 10,000-100,000 LOC: Valuable when repeatedly connecting components across the codebase
  • 100,000+ LOC: Highly valuable as autonomous agents show incomplete findings
  • 1,000,000+ LOC: Essential—only approach with progressive aggregation at extreme scale

Key trade-off: Higher token cost (1-2x) vs autonomous search, but maintains first-iteration accuracy through context isolation.

Installation:

uv tool install chunkhound

Requires Python 3.10+ and the uv package manager. See ChunkHound on GitHub for API key configuration and setup details.

ChunkHound also handles web research — searching documentation, CVEs, changelogs, and current information beyond training data. Multi-source grounding is described in Chapter 4.

Browser Automation​

Browser automation for AI agents is handled by the agent-browser CLI—a purpose-built tool that delivers consistently better results than MCP-based alternatives.

See agent-browser in CLI Tools for installation and usage.

Why CLI over MCP for browser automation:

  • Better results: Ref-based accessibility tree produces deterministic, reliable element selection
  • Token efficient: 500-2000 tokens per snapshot vs 5,000-15,000 for MCP DOM dumps
  • Simpler setup: No MCP configuration, works with any shell-capable agent
  • Faster iteration: Native Rust CLI with instant command parsing
Deprecated: MCP Browser Servers

Previous recommendations included Playwright MCP and Chrome DevTools MCP. These are now deprecated for agentic workflows—agent-browser's ref-based approach delivers more reliable automation with lower token overhead. The MCP servers remain available for legacy integrations but are not recommended for new projects.

Related Course Content: