Hawkeye Aibridge Mcp

Hawkeye AI Bridge MCP Server

Runway at 10M tokens/month - Days until a hypothetical 10M/month context budget is exhausted, if every one of 50 daily search steps looked like this one. Longer bar, more runway.

• Broad grep - 1.6 days
• Compact grep - 7.0 days
• Hawkeye indexed - 29.0 days

Local codebase search for Claude Code, VS Code, Cursor, and AI agents.

Hawkeye AI Bridge lets AI coding assistants query Hawkeye’s local project index through MCP, so they can find exact references across large codebases, assets, scripts, localization, config files, and project content without uploading the full repository.

Instead of giving an AI agent huge raw grep output, Hawkeye can return compact file/line results that help the agent decide which files are actually worth reading next.

1. Search large projects locally
2. Reduce token usage from noisy raw search output
3. Find exact references across code and non-code project files
4. Useful for C++, C#, Unreal Engine, Unity, legacy projects, and proprietary codebases
5. Hawkeye runs locally/on-premises and does not use AI for indexing or searching

---

Table of Contents

• What is this?
• Why use Hawkeye AI Bridge?
• Prerequisites
• Client Setup
  • Claude Desktop
  • Claude Code (CLI)
  • VS Code / GitHub Copilot
  • Cursor
  • OpenCode
• Installing the Skill for Claude
• Available Tools
• [Token Savings](