Enables AI coding agents to inspect GitHub repositories and shell commands for download-and-execute payloads, obfuscation, typosquatted dependencies, autorun hooks, and fake-star signals before following or running them.
A Model Context Protocol (MCP) server that provides code analysis capabilities using tree-sitter, designed to give Claude intelligent access to codebases with appropriate context management.
Audits AI agent skills for safety using static, semantic, adversarial, and supply-chain analysis, providing scores and risk flags. Can be run via CLI, CI, or as an MCP tool from Claude Code, Cursor, and Codex.
Enables MCP clients to register projects and analyze source code through Tree-sitter WASM parsing, exposing tools for AST and symbol extraction, custom queries, reference finding, complexity and similarity analysis, dependency discovery, and text search. It also ships a web studio with a Monaco editor, AST explorer, Git view, and read-only SQLite console for interactive exploration.
Enables AI clients to analyze codebases through Tree-sitter (WASM) by exposing tools for AST and symbol inspection, structural queries, reference and dependency lookup, complexity and code-similarity analysis, and project registration with directory scanning. Ships alongside a web studio with a Monaco editor, AST explorer, and read-only SQLite console.
Enables fast semantic code search and analysis across 15+ programming languages. Supports searching for functions and classes, tracing code usage, detecting syntax errors, and analyzing code quality and structure.
Enables coding agents to inspect the syntax tree of a code snippet in over two dozen supported languages, listing one named node per line with field names and zero-based row-column ranges, so they can confirm node kinds, fields, and positions before writing queries or tree-walking code.
NiceGUI MCP is a docs-first Model Context Protocol server for local NiceGUI development, providing guidance lookup, code analysis, safe fixes, and starter pattern generation.
Enables coding agents to turn existing Compose and SwiftUI previews into a static Storybook-style gallery, including setup diagnosis, coverage analysis, and generating or building the gallery. It automates the creation of browsable component catalogs for native mobile apps without requiring a SaaS account.
Enables AI coding assistants to perform local semantic code search using AST parsing and embeddings, finding code by meaning with exact file and line locations, plus AST-based usage lookup.
An MCP server that indexes source code into a local database and provides tools for querying code symbols, dependencies, and tree structure for JavaScript/TypeScript, Java, and Python.
An MCP code-intelligence server for AI agents with pre-indexed AST cache, 62 MCP tools, and TOON-compressed output, enabling token-efficient code analysis and project health grading entirely locally.
Enables static analysis, vulnerability scanning, gas optimization, formal specification verification, and audit report generation for smart contracts across Ethereum, Polygon, Arbitrum, Optimism, and Base. It also retrieves deployed contract information and audit history, persisting findings between sessions.
Lets an AI assistant drive measured Amiga reverse-engineering instruments locally — mapping ADF disks, verifying and unpacking packer blocks, reading HUNK executables, walk-based 68000 disassembly and hardware-boundary scans, static recompilation to C, and headless vAmiga screenshots and breakpoint captures compared byte-for-byte. It exposes 18 path-based tools that never fetch anything or write outside the paths they are given, returning only measurements such as entropy maps, listings, and diffs.