actor-critic-thinking
A dual-perspective thinking analysis server based on Model Context Protocol (MCP), providing comprehensive performance evaluation through Actor-Critic methodology.
claude mcp add --transport stdio aquarius-wing-actor-critic-thinking-mcp npx -y mcp-server-actor-critic-thinking
How to use
The Actor-Critic Thinking MCP server provides a dual-perspective analysis workflow. It alternates between an actor perspective (creative, empathetic viewpoint) and a critic perspective (analytical, evaluative viewpoint) to produce a balanced, multi-dimensional assessment of content, decisions, or performances. To use it, supply the required parameters: content (the current analysis text), role (either 'actor' or 'critic'), nextRoundNeeded (true or false to indicate if another round is required), thoughtNumber (starting at 1 and incremented with each round), and totalThoughts (an odd number >= 3 that represents the planned total number of thoughts). The system then returns the next perspective analysis, enabling iterative refinement and actionable feedback. This setup is ideal for evaluating artistic performances, strategic decisions, or complex scenarios requiring both empathy and objectivity.
In practice, you begin with one role (typically either actor or critic) and provide the initial content. The server will respond with the corresponding perspective analysis and guidance for the next round. When nextRoundNeeded is true, you continue with alternating perspectives, updating thoughtNumber and potentially adjusting totalThoughts as needed. The output emphasizes constructive, actionable feedback from both viewpoints, helping users bridge intention and execution across rounds.
If you integrate this MCP server into a broader workflow, you can tailor prompts to emphasize specific evaluation criteria (e.g., creativity, technical execution, audience impact) and use the multi-round structure to converge on a well-rounded assessment. Remember to maintain the odd totalThoughts constraint to ensure balanced round sequencing.
How to install
Prerequisites:
- Node.js (recommended stable LTS) and npm installed
- Basic familiarity with MCP workflows and JSON-based parameter passing
Installation steps:
-
Clone or download the repository: git clone https://github.com/your-org/actor-critic-thinking-mcp.git cd actor-critic-thinking-mcp
-
Install dependencies: npm install
-
Build the project (if applicable): npm run build
-
Run the server: node dist/index.js
or if using npm scripts: npm run start
-
(Optional) Run via npx as described in the MCP configuration: npx -y mcp-server-actor-critic-thinking
Prerequisites recap: ensure Node.js and npm are in your PATH, and that any environment-specific configuration (e.g., ports, API keys) is set prior to starting the server.
Additional notes
Tips and common considerations:
- Ensure totalThoughts is an odd number and at least 3 to maintain round balance.
- Use nextRoundNeeded to control the flow; set it to false only when the analysis is complete.
- If integrating into a larger system, consider predefining role prompts to enforce desired tone and depth for both actor and critic perspectives.
- Keep content input within the server’s expected structure to avoid parsing errors.
- When running in containers or CI, expose the appropriate ports and pass environment variables for any authentication or logging preferences.
- The provided npm package name is mcp-server-actor-critic-thinking; use the exact package name in npx commands or package managers.
- If you encounter performance delays, review the totalThoughts setting and consider reducing round count or optimizing prompt length.
Related MCP Servers
time
⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities
mcp-manager
A web-based GUI tool for managing Model Context Protocol (MCP) servers in Claude and Cursor
unity-editor
An MCP server and client for LLMs to interact with Unity Projects
website-publisher
AI Website builder and publisher MCP. Quickly publish and deploy your AI generated code as real website URL. Support html, css, js, python etc.
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.
xgmem
Global Memory MCP server, that manage all projects data.