Role-Specific Context MCP Server

What is Role-Specific Context MCP Server?

An MCP server that defines and governs contextual boundaries based on agent roles. It enables role-based context management for AI agents, allowing developers to establish clear instructions, objectives, and domain knowledge per role (e.g., Marketing Expert, Songwriter, Executive Assistant) and keep role-relevant memory partitioned and scoped.

How to use Role-Specific Context MCP Server?

Install Node.js 18+ and obtain an OpenAI API key. Clone the repository, run npm install, set the OPENAI_API_KEY in .env, then build with npm run build. Start the server with npm start. Use tools like process-with-role to send queries with a roleId, query, and optional customInstructions.

Key features of Role-Specific Context MCP Server

• Create, update, and delete custom roles with specific domains
• Pre-defined roles with tailored system prompts and instructions
• Customizable tone profiles (serious, witty, sarcastic)
• Role-specific memory storage with relevance-based retrieval
• Time-to-live (TTL) and memory limits per role
• Exposes roles as MCP resources, tools, and prompts

Use cases of Role-Specific Context MCP Server

• Process a marketing query using a pre-defined Marketing Expert role
• Create a custom Technical Writer role with instructions and tone
• Store and retrieve role-specific memories for continuous context
• Switch tone dynamically per role (e.g., witty for social media, serious for legal)
• Keep domain knowledge isolated to prevent cross-contamination between agents

FAQ from Role-Specific Context MCP Server

What are the prerequisites for running the server?

Node.js 18+ and an OpenAI API key are required.

How do I create a custom role?

Use the create-role tool with parameters id, name, description, instructions, domains, tone, and systemPrompt. Example provided for a "tech-writer" role.

How can I process a query with a specific role?

Use the process-with-role tool (or the HTTP POST endpoint /process) with roleId, query, and optional customInstructions.

What memory management features are available?

Role-specific memory storage, relevance-based retrieval, time-to-live (TTL) for memories, and configurable memory limits per role.

Which tools are exposed by the server?

Available tools: process-with-role, create-role, update-role, delete-role, change-role-tone, store-memory, and clear-role-memories.