-
Notifications
You must be signed in to change notification settings - Fork 4
Review Loop Tools
Alessio Rocchi edited this page Jan 27, 2026
·
1 revision
6 MCP tools for adversarial review loops.
Start adversarial review loop (coder ↔ adversarial).
Input:
{
"code": "function to review",
"maxIterations": 3,
"sessionId": "session-id"
}Output:
{
"success": true,
"loop": {
"id": "loop-id",
"status": "approved",
"iteration": 2,
"finalVerdict": "APPROVED"
},
"finalCode": "...",
"message": "Code approved after 2 iteration(s)"
}Get current status of review loop.
Input:
{
"loopId": "loop-id"
}Stop a running review loop.
Input:
{
"loopId": "loop-id"
}Get detailed issues from all reviews.
Input:
{
"loopId": "loop-id"
}Output:
{
"reviews": [
{
"iteration": 1,
"verdict": "NEEDS_CHANGES",
"issueCount": 2,
"issues": [...]
}
]
}List all active review loops.
Output:
{
"count": 2,
"loops": [...]
}Get current code from loop.
Input:
{
"loopId": "loop-id"
}Related:
Getting Started
Core Concepts
Agent Guides
- Overview
- Coder
- Researcher
- Tester
- Reviewer
- Adversarial
- Architect
- Coordinator
- Analyst
- DevOps
- Documentation
- Security Auditor
MCP Tools
- Overview
- Agent Tools
- Memory Tools
- Task Tools
- Session Tools
- System Tools
- GitHub Tools
- Review Loop Tools
- Identity Tools
Recipes
- Index
- Code Review
- Doc Sync
- Multi-Agent
- Adversarial Testing
- Full-Stack Feature
- Memory Patterns
- GitHub Integration
Advanced
- Plugin Development
- Custom Agent Types
- Workflow Engine
- Vector Search Setup
- Web Dashboard
- Programmatic API
- Resource Monitoring
Reference