tree-sitter-analyzer

aimasteracc/tree-sitter-analyzer

3.3

If you are the rightful owner of tree-sitter-analyzer and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Tree-sitter Analyzer is an extensible multi-language code analyzer framework using Tree-sitter with a dynamic plugin architecture, designed to solve the problem of large code files exceeding LLM single-pass token limits.

Tools

Functions exposed to the LLM to take actions

analyze_code_scale

Get code scale and complexity metrics.

format_table

Generate table-formatted analysis equivalent to CLI --table=full.

read_code_partial

Extract specific line ranges from files.

get_code_positions

Get precise position information for code elements.

analyze_code_universal

Universal code analysis with automatic language detection.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources