Skip to main content
Glama
alphaparkinc

genpark-agent-recursive-self-critique-reflection-skill

by alphaparkinc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

genpark-agent-recursive-self-critique-reflection-skill

Python 3.9+ License MIT MCP Compatible GenPark AI Zero Dependencies

🌐 GenPark MCP Hub • 📦 GenPark Official • 📖 Documentation

📌 Overview & Capability

genpark-agent-recursive-self-critique-reflection-skill is a deterministic, high-performance, zero-dependency Python tool and native Model Context Protocol (MCP) server engineered for next-generation personal agents, multi-agent frameworks, and autonomous developer workflows.

Executive Capability: Multi-agent recursive self-critique and reflection engine executing iterative evaluation-revision loops to autonomously repair logic defects, test failures, and hallucinations.

⚡ Key Highlights

  • 🐍 Zero External pip Dependencies: Implemented entirely with pure Python standard library for instant zero-overhead execution.

  • 🔌 Native Model Context Protocol (MCP): Plugs directly into any MCP-compliant client via JSON-RPC 2.0 stdio.

  • ⚡ Sub-Millisecond Execution: Slashes token burn and latency by resolving routine agent tasks deterministically without frontier LLM round-trips.

  • 🛡️ Production-Hardened: Comprehensive error handling, boundary validation, and telemetry.

Related MCP server: genpark-agent-hallucination-fact-verifier-skill

🏗️ Architecture

graph LR
    Agent([🤖 Autonomous Agent / IDE]) -->|MCP Protocol / JSON-RPC| Server[⚡ genpark-agent-recursive-self-critique-reflection-skill Server]
    Server --> Core[🧠 Deterministic Processing Core]
    Core --> Out[📊 Actionable Result & Telemetry]
    Out --> Agent

🚀 Quickstart & Usage

1. Direct Python Client Execution

python example_usage.py

2. Programmatic Integration

from client import AgentRecursiveSelfCritiqueReflection

client = AgentRecursiveSelfCritiqueReflection()
result = client.run_reflection_benchmark()
print(result)

🔌 Model Context Protocol (MCP) Setup

Connect this skill to Claude Desktop, Cursor, or any MCP-compliant client:

claude_desktop_config.json

{
  "mcpServers": {
    "genpark-agent-recursive-self-critique-reflection-skill": {
      "command": "python",
      "args": ["/path/to/genpark-agent-recursive-self-critique-reflection-skill/mcp_server.py"]
    }
  }
}

Direct MCP Testing

python mcp_server.py --test

📊 Technical Specifications

Parameter

Type

Required

Description

payload

string / dict

Yes

Primary context, text, or task input

options

dict

No

Execution flags, thresholds, or sensitivity bounds

This server cannot be deployed

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • genpark-agent-hallucination

    Alpha-Park
    F
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents and MCP clients to decompose text into atomic claims and cross-verify them against reference knowledge to flag ungrounded claims, numerical contradictions, and hallucinated entities. Runs deterministically with zero dependencies over JSON-RPC stdio, avoiding LLM round-trips for routine verification tasks.
    7
    -
  • genpark-agent-recursive-self-critique-reflection-skill by Alpha-Park

    genpark-agent-recursive-selfofficial

    Alpha-Park
    F
    license
    Not graded
    quality
    B
    maintenance
    Enables MCP clients to run deterministic, zero-dependency recursive self-critique and reflection loops over a payload and optional options, iteratively evaluating and revising agent output to autonomously repair logic defects, test failures, and hallucinations. Supports direct JSON-RPC stdio integration into MCP-compliant clients such as Claude Desktop and Cursor.
    7
    -

  • api_agent_mcp

    ewanni
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables users to define and run reusable role-based agent profiles that complete tasks alone or in bounded multi-agent discussions with independent proposals, parallel critiques, an independent judge verdict, and optional revision rounds, persisting all session events to a local SQLite log. It works over MCP stdio with any OpenAI-compatible chat completions endpoint and exposes profiles as resources.
    MIT