Rigour MCP
Enables AI agents to self-govern by scanning code for hardcoded secrets, structural violations, and AI drift in real-time, providing fix packets for automatic remediation.
README
Rigour
Your AI agent just tried to commit an AWS secret. Rigour blocked it in <100ms.
Try it now (zero config)
npx rigour-scan
Works on any repo. No init, no config, no setup. Instant results in your terminal:
HARDCODED SECRET DETECTED
AWS_SECRET_ACCESS_KEY found in src/config.ts:23
+ 22 more violations across 847 files (2.1s)
Score ████░░░░░░░░░░░░░░░░ 34/100
AI Health ███░░░░░░░░░░░░░░░░░░ 28/100
Gates: ✅ file-size ❌ security ❌ ast ✅ deps
Brain: learned 12 patterns · trend: improving ↑
Add to your AI IDE (30 seconds)
{ "mcpServers": { "rigour": { "command": "npx", "args": ["-y", "@rigour-labs/mcp"] } } }
| IDE / Agent | MCP Tools | Live Dashboard | Real-Time Feed |
|---|---|---|---|
| Claude Desktop | ✅ | ✅ MCP App | ✅ Logging |
| VS Code Copilot | ✅ | ✅ MCP App | ✅ Logging |
| ChatGPT | ✅ | ✅ MCP App | ✅ Logging |
| Goose | ✅ | ✅ MCP App | ✅ Logging |
| Claude Code | ✅ | — | ✅ Logging |
| Cursor | ✅ | — | ✅ Logging |
| Cline | ✅ | — | ✅ Logging |
| Windsurf | ✅ | — | ✅ Logging |
| Codex | ✅ | — | ✅ Logging |
Live governance dashboard (MCP App)
In supported editors, a real-time dashboard appears automatically as your agent works:
┌─ Rigour Governance ──────────────────────────┐
│ Score: 94/100 ✅ PASS │
│ │
│ 14:32:01 rigour_check → FAIL (34/100) │
│ 14:32:03 fix_packet → 8 fixes │
│ 14:32:15 rigour_check → 71/100 (+37) │
│ 14:32:22 rigour_check → ✅ PASS 94/100 │
│ │
│ Brain: 47 patterns · trend: improving ↑ │
└───────────────────────────────────────────────┘
No extra commands. The dashboard appears when the agent calls Rigour tools. Watch your agent self-heal in real time.
What it catches
| Category | Gates |
|---|---|
| Security | Hardcoded secrets (29+ patterns), SQL injection, XSS, CSRF, prototype pollution, Shannon entropy |
| Structural | File size, cyclomatic complexity, method count, parameter count, nesting depth, TODO/FIXME |
| AI Drift | Hallucinated imports, phantom APIs, context drift, retry loop detection |
| Governance | Agent team isolation, checkpoint supervision, memory DLP |
AST-based. Not heuristics. TypeScript, JavaScript, Python, Go, Ruby, C#, Java, Kotlin, Rust.
How it works
Agent writes code → Rigour gates fire → FAIL? → Fix Packet (JSON)
↓
Agent reads exact instructions
↓
Agent fixes → PASS ✓
No human in the loop. The agent gets told exactly what's wrong, on which line, and how to fix it — in JSON it can consume.
The Brain — learns your codebase
Every scan reinforces patterns. Patterns decay when absent. At strength: 0.9, they promote to hard rules. Your project's own immune system — trained locally, zero telemetry.
First week: catches 12 violations
First month: catches 8 violations ← learning your patterns
Third month: catches 3 violations ← your agents have adapted
How it's different
| Rigour | ESLint | Cloud tools | |
|---|---|---|---|
| Runs locally, zero telemetry | ✅ | ✅ | ❌ |
| Learns YOUR codebase (Brain) | ✅ | ❌ | ❌ |
| Agent self-healing (Fix Packets) | ✅ | ❌ | ❌ |
| Works offline (GGUF sidecar) | ✅ | ✅ | ❌ |
| AI-native drift detection | ✅ | ❌ | ❌ |
| MCP-native (26 tools) | ✅ | ❌ | ❌ |
Used in production
- 19,000+ total installs across CLI and MCP
- Organically forked by Alibaba iFlow
- OWASP project — listed
- Cursor MCP directory — listed
- Zero false positives on 202-finding production audit
Quick reference
npx rigour-scan # zero-config scan
npx @rigour-labs/cli init # add gates to your project
npx @rigour-labs/cli check # run gates
npx @rigour-labs/cli check --deep # + local AI analysis
npx @rigour-labs/cli check --deep --provider claude -k sk-ant-xxx # cloud AI
npx @rigour-labs/cli studio # monitoring dashboard
Architecture
| Package | Purpose |
|---|---|
@rigour-labs/core |
Gate engine, AST analysis, Fix Packets, Brain |
@rigour-labs/cli |
init, check, scan, run, studio |
@rigour-labs/mcp |
MCP server — 26 tools for agent integration |
rigour-scan |
Zero-config shortcut: npx rigour-scan |
Stack: TypeScript strict, web-tree-sitter, Zod, Vitest.
Full docs | Technical Spec | Philosophy
MIT © Rigour Labs — Built by Ashutosh
If Rigour caught something real in your codebase — tell us.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。