A local-first, framework-aware token reduction engine — a polyglot AST semantic proxy and MCP server. It prunes implementation bodies out of dependency files while preserving every type signature, interface, and module export, so LLM agents see the full shape of the code at a fraction of the tokens.

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "token-shrink": {
      "command": "npx",
      "args": [
        "-y",
        "ajdev0/token-shrink"
      ]
    }
  }
}

README Excerpt

A **local-first, framework-aware token reduction engine** — a polyglot AST semantic proxy and MCP server. It prunes implementation bodies out of **dependency files** while preserving every type signature, interface, and module export, so LLM agents see the full shape of the code at a fraction of the tokens.

Tools (9)

GETPOSTactiveFilePathblockcompound_statementincludeStatsmaxSkeletonsstatement_blockstatements

token-shrink

Quick Install

README Excerpt

Tools (9)

Related AI/LLM Servers