References the original recursive-companion repository as inspiration, with this implementation adding incremental processing capabilities
Recursive Companion MCP
An MCP (Model Context Protocol) server that implements iterative refinement through self-critique cycles. Inspired by Hank Besser's recursive-companion, this implementation adds incremental processing to avoid timeouts and enable progress visibility.
Features
Incremental Refinement: Avoids timeouts by breaking refinement into discrete steps
Mathematical Convergence: Uses cosine similarity to measure when refinement is complete
Domain-Specific Optimization: Auto-detects and optimizes for technical, marketing, strategy, legal, and financial domains
Progress Visibility: Each step returns immediately, allowing UI updates
Parallel Sessions: Support for multiple concurrent refinement sessions
Auto Session Tracking: No manual session ID management needed
AI-Friendly Error Handling: Actionable diagnostics and recovery hints for AI assistants
How It Works
The refinement process follows a Draft → Critique → Revise → Converge pattern:
Draft: Generate initial response
Critique: Create multiple parallel critiques (using faster models)
Revise: Synthesize critiques into improved version
Converge: Measure similarity and repeat until threshold reached
For detailed architecture diagrams and system design documentation, see ARCHITECTURE.md.
Installation
Prerequisites
Python 3.10+
uv package manager
AWS Account with Bedrock access
Claude Desktop app
Setup
Clone the repository:
Install dependencies:
Configure AWS credentials as environment variables or through AWS CLI
Add to Claude Desktop config (
~/Library/Application Support/Claude/claude_desktop_config.json
):
Basic Configuration:
Optimized Configuration (Recommended):
Performance Tips:
Use Haiku for
CRITIQUE_MODEL_ID
for 50% speed improvementLower
CONVERGENCE_THRESHOLD
to 0.95 for faster convergenceReduce
PARALLEL_CRITIQUES
to 2 for better resource usageSee API_EXAMPLES.md for more configuration examples
Usage
The tool provides several MCP endpoints for iterative refinement:
Quick Start Examples
Simple refinement (auto-complete):
Step-by-step refinement (full control):
Session management:
Complete API Reference
For comprehensive examples with realistic scenarios, error handling patterns, and integration workflows, see API_EXAMPLES.md.
Available Tools
start_refinement
- Begin new refinement session with domain detectioncontinue_refinement
- Advance session through draft→critique→revise cyclesget_final_result
- Retrieve completed refinementget_refinement_status
- Check progress without advancingcurrent_session
- Get active session info (no ID needed)list_refinement_sessions
- See all active sessionsabort_refinement
- Stop refinement, return best version so farquick_refine
- Auto-complete simple refinements (under 60s)
Configuration
Environment Variable | Default | Description |
| anthropic.claude-3-sonnet-20240229-v1:0 | Main generation model |
| Same as BEDROCK_MODEL_ID | Model for critiques (use Haiku for speed) |
| 0.98 | Similarity threshold for convergence (0.90-0.99) |
| 3 | Number of parallel critiques per iteration |
| 10 | Maximum refinement iterations |
| 300 | Timeout in seconds |
Performance
With optimized settings:
Each iteration: 60-90 seconds
Typical convergence: 2-3 iterations
Total time: 2-4 minutes (distributed across multiple calls)
Using Haiku for critiques reduces iteration time by ~50%.
AI-Friendly Features
This tool includes special features for AI assistants using it:
Auto Session Tracking: The
current_session_id
is automatically maintainedSmart Error Messages: Errors include
_ai_
prefixed fields with actionable diagnosticsPerformance Hints: Responses include optimization tips and predictions
Progress Predictions: Convergence tracking includes estimates of remaining iterations
Example AI-helpful error response:
Architecture
Development
Running tests
Local testing
Automation Infrastructure
This project includes comprehensive automation for OSS readiness:
🤖 Dependabot: Automated dependency updates with intelligent grouping
🚀 Semantic Release: Automated versioning and releases based on conventional commits
🔒 Security Monitoring: Multi-tool security scanning (Safety, Bandit, CodeQL, Trivy)
✅ Quality Gates: Automated testing, coverage, linting, and type checking
📦 Dependency Management: Advanced dependency health monitoring and updates
Automation Commands
Development Workflow
Feature Development: Work on feature branches
Pull Requests: Quality gates run automatically
Code Review: Automated security and quality feedback
Merge to develop: Beta releases created automatically
Merge to main: Production releases created automatically
See AUTOMATION.md for complete automation documentation.
Attribution
This project is inspired by recursive-companion by Hank Besser. The original implementation provided the conceptual Draft → Critique → Revise → Converge pattern. This MCP version adds:
Session-based incremental processing to avoid timeouts
AWS Bedrock integration for Claude and Titan embeddings
Domain auto-detection and specialized prompts
Mathematical convergence measurement
Support for different models for critiques vs generation
Contributing
Contributions are welcome! Please read our Contributing Guide for details.
License
MIT License - see LICENSE file for details.
Acknowledgments
Original concept: Hank Besser's recursive-companion
Built for the Model Context Protocol
Uses AWS Bedrock for LLM access
Inspired by iterative refinement patterns in AI reasoning
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
An MCP server that implements iterative refinement of responses through self-critique cycles, breaking the process into discrete steps to avoid timeouts and show progress.
Related MCP Servers
- AsecurityAlicenseAqualityAn adaptation of the MCP Sequential Thinking Server designed to guide tool usage in problem-solving. This server helps break down complex problems into manageable steps and provides recommendations for which MCP tools would be most effective at each stage.Last updated -1614380MIT License
- -securityFlicense-qualityAn advanced MCP server that implements sophisticated sequential thinking using a coordinated team of specialized AI agents (Planner, Researcher, Analyzer, Critic, Synthesizer) to deeply analyze problems and provide high-quality, structured reasoning.Last updated -1251
- AsecurityAlicenseAqualityAn advanced MCP server that provides interactive feedback mechanisms with support for various feedback types, multi-language capabilities, and team collaboration features for AI tools like Cursor, Cline, and Windsurf.Last updated -41MIT License
- -securityFlicense-qualityAn MCP server that implements Retrieval-Augmented Generation to efficiently retrieve and process important information from various sources, providing accurate and contextually relevant responses.Last updated -