Actor-Critic Thinking MCP Server
A dual-perspective thinking analysis server based on Model Context Protocol (MCP), providing comprehensive performance evaluation through Actor-Critic methodology.
Showcase

Without Actor-Critic Thinking

Features
- Dual-perspective Analysis: Alternates between actor (creator/performer) and critic (analyzer/evaluator) perspectives
- Round Tracking: Tracks rounds of dual-perspective analysis
- Balanced Assessment: Combines empathetic understanding with objective analysis
- Multi-dimensional Evaluation: Generates nuanced, multi-dimensional assessments
- Actionable Feedback: Provides constructive improvement suggestions
Use Cases
- Evaluating artistic performances, creative works, or strategic decisions
- Analyzing the gap between intention and execution
- Providing constructive feedback that considers both creative vision and technical execution
- Reviewing complex scenarios that require both empathy and objectivity
- Situations requiring balanced assessment of subjective and objective criteria
- Performance reviews that need both self-reflection and external evaluation
- Creative processes that benefit from iterative refinement
Parameters
Required Parameters
content(string): Current analysis content from the specified role perspectiverole(string): Perspective role, options:"actor": Actor perspective (empathetic/creative viewpoint)"critic": Critic perspective (analytical/evaluative viewpoint)
nextRoundNeeded(boolean): Whether another round of actor-critic dialogue is neededthoughtNumber(integer): Current thought number in the sequence (minimum: 1)totalThoughts(integer): Total number of thoughts planned (must be odd and >= 3)
Role Perspective Guidelines
Actor perspective should include:
- Understanding intentions, creative choices, emotional context, challenges faced
- Self-reflection on performance and decision-making process
- Explanation of creative vision and goals
Critic perspective should include:
- Technical execution analysis, effectiveness evaluation
- Audience impact assessment, comparative analysis
- Objective feedback and improvement suggestions
How to use
{
"mcpServers": {
"actor-critic-thinking": {
"command": "npx",
"args": ["-y", "mcp-server-actor-critic-thinking"]
}
}
}
Installation and Running
# Build the project
npm run build
# Run the server
node dist/index.js
Example Usage
System prompt:
Your task is to generate creative, memorable, and marketable product names based on the provided description and keywords. The product names should be concise (2-4 words), evocative, and easily understood by the target audience. Avoid generic or overly literal names. Instead, aim to create a name that stands out, captures the essence of the product, and leaves a lasting impression.
User prompt:
Description: A noise-canceling, wireless, over-ear headphone with a 20-hour battery life and touch controls. Designed for audiophiles and frequent travelers. Keywords: immersive, comfortable, high-fidelity, long-lasting, convenient
Best Practices
- Start with either actor or critic perspective
- Alternate between perspectives to maintain balance
- Continue rounds until comprehensive analysis is achieved
- Focus on relevant performance aspects
- Generate balanced assessments that honor both perspectives
- Provide constructive, actionable feedback
- Only set
nextRoundNeededto false when analysis is complete
Recommend MCP Servers 💡
@notainc/gyazo-mcp-server
An official Model Context Protocol server for Gyazo, enabling AI assistants to access, search, fetch, and upload images and their metadata (including OCR data) via the Gyazo API.
@zcaceres/gtasks
A Google Tasks Model Context Protocol Server for Claude
Chazzychouse/weather-mcp-server
A basic MCP server implementation for weather data using the NOAA API, providing forecast and alert tools.
pubchem-mcp
An MCP server for accessing PubChem data, providing tools for querying compounds, substances, bioassays, and related chemical information.
mcp-visualization-duckdb
An MCP server that transforms natural language into interactive data visualizations using DuckDB and Databricks, integrated with Claude Desktop.
Home-assistant
A Model Context Protocol Server for Home Assistant