菜单
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Agent-to-User Interface (A2UI) protocol implementation and client renderer scaffolding.
Infrastructure automation, configuration management, and application deployment orchestration using Ansible.
Create and manage unicode braille animations and spinners for CLIs and web apps. Use this skill when the user wants to add loading indicators, progress animations, or custom braille-based art to their terminal or browser-based application.
Agent harness for headlessly deploying Code Scaffold assets.
Comprehensive cybersecurity arsenal integrating MITRE and NIST framework methodologies, NVIDIA SkillSpector vulnerability scanning, and deep SAST secret detection.
Specialized skill for crawling and scraping websites to convert them to LLM-ready clean markdown or structured data using Firecrawl API and CLI.
| name | Codebase Memory MCP |
| description | High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. |
| version | 1 |
Codebase Memory MCP is an ultra-fast code intelligence engine designed specifically for AI agents. Rather than dumping raw files into context, it builds a persistent structural knowledge graph (AST + Hybrid LSP) and provides tools to query it.
Because this tool ships as a single static binary with zero dependencies, AI agents can effortlessly bootstrap it in any workspace.
Invoke-WebRequest -Uri https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.ps1 -OutFile install.ps1
Unblock-File .\install.ps1
.\install.ps1 --skip-config
curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash -s -- --skip-config
Note: The --skip-config flag is recommended for headless agent bootstrapping if you intend to launch the server directly via standard MCP stdio pipes rather than relying on global IDE configs.
To maximize efficiency during autonomous tasks, leverage this tool to perform structural analysis before reading files:
grep operations and token bloat.