Memory Context Provider (MCP) Server
A server that manages context for LLM interactions, storing and providing relevant context for each user.
Features
- In-memory storage of user contexts
- Context management with last 5 prompts
- RESTful API endpoints
- TypeScript support
Setup
Install dependencies:
npm install
Start the development server:
npm run dev
API Endpoints
POST /context/:userId
Add a new prompt to user’s context and get updated context.
Request body:
{
"prompt": "Your prompt here"
}
Response:
{
"context": "Combined context from last 5 prompts"
}
GET /context/:userId
Get current context for a user.
Response:
{
"context": "Current context"
}
DELETE /context/:userId
Clear context for a user.
Response:
{
"message": "Context cleared"
}
Development
npm run dev
: Start development server with hot reloadnpm run build
: Build TypeScript filesnpm start
: Run built files
Memory Context Provider Server
Project Details
- Srish-ty/MCP-Testing-interface-for-LLMs
- mcp-server
- Last Updated: 3/30/2025
Recomended MCP Servers
A MCP Server to know about Zaragoza tram system in realtime
A high-throughput and memory-efficient inference and serving engine for LLMs
MCP for judged outputs between two AIs for a better output
This repo is an extension of PostgreSQL MCP Server providing functionalities to create tables, insert entries, update entries,...
MCP Server for interacting with live music events
MCP server to access Garmin data
Claude can perform Web Search | Exa with MCP (Model Context Protocol)