ast-grep MCP is a locally run server that lets AI coding assistants search code by its syntax structure. It connects ast-grep to Cursor, Claude Desktop and other clients that support the Model Context Protocol (MCP). It's for developers who need an assistant to find specific code constructs when matching words alone is too broad.
An assistant can look for function calls, declarations, classes or imports, then narrow a search to relationships within the code. For example, it can find async functions containing an await expression, or code nested inside a particular construct. Simple patterns cover straightforward searches; YAML rules express more detailed conditions, including what a match contains and what comes before or after it.
The server also lets assistants test rules against code snippets before searching a whole codebase. Its syntax-tree inspection tool exposes how the parser sees a snippet, which helps diagnose patterns that miss their intended matches. Search results can include readable code with file locations or JSON with fuller metadata.
The Python server uses a local ast-grep installation for code analysis and requires an MCP-compatible client. It provides search tools rather than an AI model of its own. The project is open source under the MIT license. Language support comes from ast-grep and includes JavaScript, TypeScript, Python, Rust, Go, Java, C/C++ and C#. Custom ast-grep configuration can add language support.
The maintainers describe this MCP server as experimental.
Claim this page and we'll verify you by hand. ast-grep MCP gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find ast-grep MCP?Promote it
Something wrong or outdated on this page?
62.5KUpdated 2 days agoMIT
#MCP#RAG#Tool calling
Context7 brings current library documentation and code examples into an AI coding assistant's context. It's for developers who want answers grounded in the libraries and versions they're actually using, rather than an assistant's older training data. It works with Claude Code, Codex, Cursor, Devin Desktop and Antigravity.
28.6KUpdated 2 days agoMIT
Docker · Web · Browser Extension#Agent Skills#Code execution#MCP
29.9KUpdated 1 day ago
Docker · JetBrains#Code execution#MCP#Persistent memory
269.7KUpdated 20 hours agoMIT
Windows#Guardrails#MCP#Multi-agent workflows
272.1KUpdated 1 day agoMIT
#Agent Skills#Git integration#Multi-agent workflows
293KUpdated 5 days agoMIT
Windows#Agent Skills#Code execution#Git integration
Repomix turns a code repository into a single file that an AI assistant can read. It’s for developers who need to give Claude, ChatGPT, Gemini, or another model enough project context for code review or analysis. You can use its command line on your own machine, pack a repository through its website, or run it as an MCP server, including through Docker. It is open source under the MIT license.
Serena is a locally run MCP toolkit that gives AI coding agents access to code structure: functions, classes and the references between them. It's for developers who want their agent to find and change specific parts of a codebase without reading whole files or relying on text matching. It requires an LLM client and works with Claude Code, Codex, OpenCode, Cursor and OpenWebUI.
ECC is a free, MIT-licensed open source toolkit that adds repeatable engineering workflows to coding assistants. It runs alongside your chosen agent and works with self-hosted models or cloud providers through that agent's supported endpoints. It's for developers who want planning, testing and review to follow a consistent process across coding sessions.
Skills (mattpocock) is an MIT-licensed collection of engineering workflows for developers using Claude Code, Codex and other AI coding agents. Its small, separate skills work with any model and can be combined or adapted to your project, so you can choose specific practices without adopting an entire development process.
Superpowers adds a structured development process to AI coding assistants. It's for developers who want their agent to agree on a design before writing code, follow an implementation plan, and check its work against that plan. The open-source framework uses the MIT license and works inside coding tools including Claude Code, Codex, Cursor, Gemini CLI and OpenCode.