leveret
leveret
leveret 是指幼小的野兔——体型小、速度快,出生时眼睛就是睁开的。
leveret 是一个自托管的混合引擎,用于私有代码审查:它是托管式 AI 审查机器人的继任者,适用于代码留在本地的团队。它提供确定性静态分析、AST 级搜索和分级过滤管道,通过 MCP 暴露,由你带来的任何审查代理驱动(BYOM——Claude Code、通过任何支持 MCP 的客户端的本地模型,或 CI 运行器)。引擎层本身从不调用 LLM。
项目所针对的管道:
[diff] → [deterministic first pass: leveret scan] → [review agent: leads → concerns]
→ [verification agent: refute-or-evidence filter] → [report]工具
scan
{repo, base? | files?, engines?, delta?}— 运行适用于变更集的引擎,并返回规范化发现(engine, rule, severity, file, line, message, provenance)以及每个引擎的状态报告。当提供 base 引用时,扫描默认进行增量:已存在于基础树中的发现会被视为预先存在而丢弃(会被计数,但不会静默),幸存者会被标记为introduced。引擎:semgrep(注册表安全 + 各语言规则集)、gitleaks(base..HEAD提交中的密钥)、shellcheck、ruff、actionlint、zizmor(工作流安全)、osv-scanner(锁文件 CVE)、typos(拼写)、jscpd(按配置文件门控的重复检测)、配置文件声明的 semgrep/ast-grep 规则包,以及通过custom:配置文件条目运行的任意 SARIF 输出命令(recipes:psalm taint、hadolint、trivy 等)。发现是审查线索,而非结论。ast_search
{repo, pattern, lang, paths?}— 通过 ast-grep 进行结构化模式匹配(元变量、语法感知),用于文本 grep 会出错的调用点形状问题。context
{repo, files}— 优先级信号,而非发现:每个函数的圈复杂度(lizard)、12 个月变更率、最后修改日期。
Related MCP server: reporelay
运行
npm install && npm run build
node dist/server.js # stdio MCP server
npm test # integration tests (need semgrep, gitleaks, shellcheck, ruff, actionlint, ast-grep on PATH)Claude Code 注册:
claude mcp add leveret -- node /Users/andre/git/leveret/dist/server.js状态 / 路线图
参见 DESIGN.md — 架构、三级过滤器(可操作 / 定价噪声 / 误报)、仓库内记忆存储、代理提示词契约,以及控制采用的验证基准。
许可证
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseAqualityAmaintenanceLocal-first code intelligence MCP server with hybrid BM25 + ONNX vector search, symbol-level impact analysis, diff-aware PR review with risk scoring, and persistent memory tied to git state.3669576MIT
- AlicenseNot gradedqualityFmaintenanceSelf-hosted MCP server for indexing and searching code repositories via hybrid search and deep code understanding.718MIT
- AlicenseNot gradedqualityCmaintenanceOpen-source AI code review MCP server for local git diff auditing with deterministic security rules and AI-powered analysis using any OpenAI-compatible model.4MIT
- AlicenseNot gradedqualityBmaintenanceMCP server for automated code review using AI agents. It analyzes code diffs or file paths for bugs, security issues, and style violations.MIT
Related MCP Connectors
Enterprise code intelligence for M&A, security audits, and tech debt. Hosted server with 200k free.
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/andrebrait/leveret'
If you have feedback or need assistance with the MCP directory API, please join our Discord server