Role-Specific Context MCP Server

@Chris-June

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

Chris-June

Role-Specific Context MCP Server について

概要はまだありません

#mcp-server#role-management#context-management

Role-Specific Context MCP Server の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

Role-Specific Context MCP Server のツール

Process a query using a specific role

Create a new role

Update an existing role

Delete a custom role

Change the tone of a role

Store a memory for a specific role

Clear all memories for a role

概要

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

よくある質問

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`.

「その他」の他のコンテンツ

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K