Recursive Thinking MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Recursive Thinking MCP ServerStart a thinking session to design a secure JWT authentication system"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Chain-of-Thought Recursive Thinking MCP Server
v2.2.0 - Expert Roles, Custom Checklists, and Strict Validation!
Token-efficient MCP server that makes AI agents think deeper through structured reasoning chains, self-critique, and automatic rethinking loops.
π― What's New in v2.2.0
Feature | Description | Benefit |
Expert Roles | AI assumes specific personas (e.g., Security Architect) | Rigorous perspective-based thinking |
Custom Checklists | Validate solutions against specific requirements | Tailored quality enforcement |
Strict Mode | Prevents finalization unless all criteria are met | High-bar production quality |
Chain of Thought | AI explains WHY it chose each solution | Transparent reasoning, better decisions |
Self-Evaluation | AI rates its own solutions (1-10 scale) | Honest assessment of solution quality |
Rethink Loop | Automatic rethinking if rating <7 or issues found | Continuous improvement |
Related MCP server: cortex-mcp
β¨ Features
π§ Chain of Thought: AI must explain reasoning behind every decision
π Expert Roles: Inject specialized expertise into the thinking process
π Custom Checklists: Force AI to validate against your specific requirements
βοΈ Strict Mode: Ensure the AI never settles for "good enough"
π Self-Evaluation: AI rates solutions with score (1-10), good/bad flag, and rationale
π Continuous Rethinking: Automatically rethinks if solution scored <7 or has weaknesses
π― Phase-Based Workflow: Structured 5-phase thinking process
π° Token Optimized: Smart compression, phase-focused prompts (~70% reduction)
π How It Works
The 5 Phases
βββββββββββββββ
β 1. EXPLORE β βββ Propose solution with reasoning & expert perspective
ββββββββ¬βββββββ
βΌ
βββββββββββββββ
β 2. JUSTIFY β βββ Critically examine reasoning & assumptions
ββββββββ¬βββββββ
βΌ
βββββββββββββββ
β 3. EVALUATEβ βββ Rate solution (1-10) against checklist
ββββββββ¬βββββββ
βΌ
βββββ΄ββββ
β Score β
β β₯7? β ββNOββ βββββββββββββββ
βββββ¬ββββ β 4. RETHINK β βββ Improve based on weaknesses
βYES ββββββββ¬βββββββ
βΌ β
βββββββββββββββ β
β 5. FINALIZEβ ββββββββββββ
βββββββββββββββπ Usage
Starting a Thinking Session with Advanced Config
await mcp.callTool('recursive_thinking', {
action: 'start',
task: 'Design a highly available database schema for a global payment system',
config: {
role: 'Database Reliability Engineer',
checklist: [
'Must handle 10k transactions/sec',
'ACID compliance mandatory',
'Multi-region failover strategy',
'Data encryption at rest and in transit'
],
strictMode: true,
minRating: 8
}
});βοΈ Configuration Options
Parameter | Type | Default | Description |
| string | - | Expert persona to assume (e.g., 'Senior DevOps') |
| string[] | [] | Specific requirements to validate against |
| boolean | false | If true, fails instead of finalizing if criteria aren't met |
| number | 5 | Maximum recursion depth |
| number | 0.85 | Stop when confidence meets threshold |
| number | 7 | Minimum acceptable score (1-10) |
| boolean | true | Enable continuous refinement loop |
π¦ Installation
npx -y recursive-thinking-mcpπ License
MIT
π Links
This server cannot be deployed
Maintenance
Related MCP Connectors
Build, validate, and deploy multi-agent AI solutions from any AI environment.
Reduces AI Agent token usage by 40% via three-stage SOP workflow.
Create and manage AI agents that collaborate and solve problems through natural language interactiβ¦
Verified 2-3 step AI-agent missions with whole-transaction success-only charging.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides 10 structured reasoning strategies (Chain of Thought, ReAct, Tree of Thoughts, etc.) for complex problem-solving with session persistence, branching, and tool integration capabilities.37 npm28MIT
- AlicenseAqualityCmaintenanceEnables multi-level reasoning with configurable depth levels, session-based state management, structured thought input, and real-time trace resources.125 npm1MIT
- AlicenseAqualityBmaintenanceEnables AI agents to perform dynamic and reflective problem-solving through a chain of thoughts, allowing them to break down complex problems, revise past thoughts, and explore logic branches before reaching a conclusion.1106,759 npm-
- AlicenseNot gradedqualityBmaintenanceProvides persistent cross-session AI memory, code graph analysis, and subagent context compression so coding agents can resume work instantly and avoid re-reading the codebase.Elastic 2.0