MCP-Server
by Chris-June
The Role-Specific Context MCP Server defines and governs contextual boundaries based on agent roles in your system. It enables role-based context management for AI agents, allowing you to establish clear instructions and objectives for each role.
Last updated: N/A
What is MCP-Server?
This MCP server enables role-based context management for AI agents. It allows you to define roles with specific instructions, objectives, and domain knowledge, keeping role-relevant memory partitioned and scoped.
How to use MCP-Server?
To use the server, first install the prerequisites (Node.js 18+ and OpenAI API key). Then, clone the repository, install dependencies using npm install, set up the environment variables, and build the project using npm run build. Finally, run the server using npm start or npm run start:http for testing. You can interact with the server using MCP tools and prompts or through the HTTP API.
Key features of MCP-Server
Role Management (create, update, delete roles)
Pre-defined roles with specific expertise domains
Role-specific system prompts and instructions
Customizable tone profiles
Role-specific memory storage
Memory retrieval based on relevance
Time-to-live (TTL) for memories
Exposes roles as MCP resources
Provides tools for role management and query processing
Use cases of MCP-Server
Creating AI agents with specialized expertise (e.g., Marketing Expert, Songwriter)
Managing context for AI agents in different domains
Adapting the tone and style of AI agents based on their role
Building AI applications that require role-based access control
Implementing AI-powered customer support with role-based agents
FAQ from MCP-Server
What is the purpose of this server?
What is the purpose of this server?
The server provides role-based context management for AI agents, allowing you to define and manage roles with specific instructions, objectives, and domain knowledge.
What are the prerequisites for running the server?
What are the prerequisites for running the server?
You need Node.js 18+ and an OpenAI API key.
How do I configure the server?
How do I configure the server?
You can configure the server by modifying src/config.ts.
How do I create a new role?
How do I create a new role?
You can use the create-role tool or the create-custom-role prompt.
How do I process a query with a specific role?
How do I process a query with a specific role?
You can use the process-with-role tool or the role-{roleId} prompt, or the HTTP API endpoint /process.