
Rigour
Runs quality gates on your codebase through MCP, exposing 26 tools that let AI agents check for hardcoded secrets, structural issues, and AI-specific drift like hallucinated imports. Gates fire automatically when agents write code and return Fix Packets with exact line numbers and remediation steps agents can consume directly. The Brain learns your codebase patterns over time, promoting recurring violations to hard rules. Works with TypeScript, JavaScript, Python, Go, Ruby, and more through AST analysis. Includes a live dashboard in Claude Desktop and VS Code that shows real-time pass/fail scores as agents iterate. Add it with npx and point your MCP config at @rigour-labs/mcp to get instant governance without leaving the agent loop.
- GitHub stars
- 29
- tools
- 9
- transport
- STDIO
- last updated
- Oct 19, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
rigour_checkRun quality gate checks on the project. Matches the CLI 'check' command.1 params
Run quality gate checks on the project. Matches the CLI 'check' command.
cwdstringrigour_explainExplain the last quality gate failures with actionable bullets. Matches the CLI 'explain' command.1 params
Explain the last quality gate failures with actionable bullets. Matches the CLI 'explain' command.
cwdstringrigour_statusQuick PASS/FAIL check with JSON-friendly output for polling current project state.1 params
Quick PASS/FAIL check with JSON-friendly output for polling current project state.
cwdstringrigour_get_fix_packetRetrieves a prioritized 'Fix Packet' (v2 schema) containing detailed machine-readable diagnostic data.1 params
Retrieves a prioritized 'Fix Packet' (v2 schema) containing detailed machine-readable diagnostic data.
cwdstringrigour_record_failureRecord an operation failure to track retry loops and prompt for documentation consult.3 params
Record an operation failure to track retry loops and prompt for documentation consult.
categorystringcwdstringerrorMessagestringrigour_clear_failureClear failure history for a category after a successful operation or manual fix.2 params
Clear failure history for a category after a successful operation or manual fix.
categorystringcwdstringrigour_rememberStore a persistent instruction or context that the AI should remember across sessions. Use this to persist user preferences, project conventions, or critical instructions that the agent should always follow.3 params
Store a persistent instruction or context that the AI should remember across sessions. Use this to persist user preferences, project conventions, or critical instructions that the agent should always follow.
cwdstringkeystringvaluestringrigour_recallRetrieve stored instructions or context. Call this at the start of each session to restore memory. Returns all stored memories if no key specified.2 params
Retrieve stored instructions or context. Call this at the start of each session to restore memory. Returns all stored memories if no key specified.
cwdstringkeystringrigour_forgetRemove a stored memory by key.2 params
Remove a stored memory by key.
cwdstringkeystringSponsors
Readme
Rigour
A reviewer that knows how your team works, whichever agent writes the code.
Whichever agent your engineers use, its work arrives already shaped by how your team builds software, and it gets closer to your standards every week.
Teams used to carry their judgment through people: the senior who briefed you before you started, the reviewer who caught what you missed, the engineer who remembered why the last attempt failed. Coding agents write faster than any person can brief, review or remember. The knowledge is still in your team; Rigour is how it reaches every agent, at the speed agents work.
Works with Claude Code, Cursor, Codex, Cline and Windsurf. Free, open source, and runs on your machine.
Details
- Repository
- github.com/rigour-labs/rigour
- Package
@rigour-labs/mcp- Transport
- STDIO
- Registry
- MCP registry, active