AST2LLM for Go
About
An AST-powered tool that enhances LLM context by automatically injecting relevant Go code structures into prompts.
Details
- Author
- ast2llm
- Categories
- Developer Tools
Jump to
Setup
Install AST2LLM for Go in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/ast2llm/ast2llm-go
Follow the installation instructions in the repository README, then restart your MCP client.
Local AST-powered context enhancement tool for LLM
Automatically injects relevant code structure into your prompts using precise Go AST analysis.
Our MCP server provides theparse-gotool that:
- Analyzes your Go project structure
- Identifies external type declarations
- Packages context for LLM prompts
- Delivers 3-5x faster context resolution than grap-based approaches
For example, the demo above shows the model calling the tool to get the missing information about the fields of theMyDTOstructure. In response, the model received all the necessary information from the response:
Used Imported Structs (from this project, if available): Struct: testme/dto.MyDTO Fields: - Foo string - Bar int
- Go 1.22 or higher (if building from source)
- Supported MCP client (Cursor, Claude, VS Code, etc.)
To installast2llm-goon your system, run the following command in your terminal:
curl -LsSf https://raw.githubusercontent.com/ast2llm/ast2llm-go/main/install.sh | sh
This script will automatically detect your OS and architecture, download the appropriate binary, and attempt to add it to your PATH. You can also specify an installation directory:
curl -LsSf https://raw.githubusercontent.com/ast2llm/ast2llm-go/main/install.sh | sh -s -- --install-dir /usr/local/bin
To updateast2llm-goto the latest version, simply re-run the installation command:
curl -LsSf https://raw.githubusercontent.com/ast2llm/ast2llm-go/main/install.sh | sh
To removeast2llm-gofrom your system, run the uninstallation script:
curl -LsSf https://raw.githubusercontent.com/ast2llm/ast2llm-go/main/uninstall.sh | sh
This script will remove the binary, clean up PATH modifications, and delete related configuration files. You may need to restart your shell after uninstallation.
After installationast2llm-go, you need to restart the IDE.
{ "mcpServers": { "go-ast": { "command": "ast2llm-go", "args": [] } } }
{ "mcpServers": { "go-ast": { "command": "ast2llm-go" } } }
{ "servers": { "go-ast": { "type": "stdio", "command": "ast2llm-go" } } }
This MCP server is under active development and may have stability issues or incomplete functionality. We're working hard to improve it, but you might encounter:
- Occasional parsing errors
- Limited type support in current version
- Performance bottlenecks with large codebases
Found an issue?
Open a GitHub Issueto help us improve! We appreciate all bug reports and feature requests.
- Support for struct types
- Support for interface types
- Support for function types
- Support for global variables
- Analyze multiple open files simultaneously
- Cross-file dependency resolution
- Context-aware import optimization
- Improved type hierarchy visualization
- Research optimal AST representation for LLMs. Provide different output formats tailored to various scenarios like inrepomix:
- XML: For compatibility with traditional solutions akin to Repomix.
- JSON: A modern format suitable for integration with contemporary tools and environments.
- Markdown: An easily readable format ideal for quick viewing and documenting changes.
- Incremental parsing
- AST caching
- Parallel analysis
We welcome contributions! Here's how you can help:
- Open an issue with a clear description
- Include steps to reproduce
- Add relevant logs/screenshots
- Open an issue with the feature request
- Explain the use case and benefits
- Include any relevant examples
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Ensure all tests pass
- Submit a PR with a clear description
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
Local stdio MCP server that lets AI coding agents read and maintain structured architecture, rules, and decisions directly from your repository.
Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.
Remote, no-auth MCP server providing AI-powered codebase context and answers
Instead of direct calling MCP tools, mcpcode server transforms MCP tool calls into TypeScript programs, enabling smarter, lower-latency orchestration by LLMs.
Help agents automatically write and test stories for your UI components
Official Svelte MCP server, provides docs and suggestions on the generated code.
Supercharge your Agent with Semantic Code Intelligence and save 💰 in the process!
Execute any LLM-generated code in the YepCode secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
