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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.