๐Ÿง  Memory MCP Server - Orchestrator

SSE

by rashee1997

383 downloads Not rated yet MIT license

About

Your AI Agent's Persistent Brain - A Comprehensive Memory & Task Management System

Details

Transport
SSE
License
MIT license

Explore

- Conversation history with full context storage
- Versionโ€‘controlled dynamic context storage
- Knowledge graph for entity relationship management
- Vector embeddings for semantic search
- AIโ€‘powered planning with hierarchical tasks and dependencies
- Google Gemini integration for prompt refinement, summarization, and more
- Tavily web search integration
- Data validation, logging, backup, and restore

<div align="center">

| Requirement | Version | Required |
|------------|---------|----------|
| Node.js | 18.x or higher | โœ… |
| npm | Latest | โœ… |
| Git | Any | โœ… |

</div>


npm install

npm run test


dockerfile

The server requires API keys for external services. These should be configured in your MCP client settings.

<div align="center">

| Service | Environment Variable | Required | Get API Key |
|---------|---------------------|----------|-------------|
| Google Gemini | GEMINI_API_KEY | โœ… | Get Key |
| Tavily Search | TAVILY_API_KEY | โœ… | Get Key |

</div>


npm install

<details>
<summary><b>Example 1: Creating an AI-Generated Plan</b></summary>

typescript
// 1. Refine the user prompt
const refinedPrompt = await refine_user_prompt({
agent_id: "my-agent",
raw_user_prompt: "Build a REST API for user management"
});

// 2. Create a plan from the refined prompt
const plan = await create_task_plan({
agent_id: "my-agent",
refined_prompt_id: refinedPrompt.refined_prompt_id
});

// 3. Get AI suggestions for subtasks
const subtasks = await ai_suggest_subtasks({
agent_id: "my-agent",
plan_id: plan.plan_id,
parent_task_id: plan.task_ids[0]
});


</details>

<details>
<summary><b>Example 2: Knowledge Graph Operations</b></summary>

typescript
// Create entities
await knowledge_graph_memory({
agent_id: "my-agent",
operation: "create_entities",
entities: [
{
name: "UserController",
entityType: "class",
observations: ["Handles user CRUD operations"]
}
]
});

// Query with natural language
const results = await kg_nl_query({
agent_id: "my-agent",
query: "What classes handle user operations?"
});
```

</details>

---

store_conversation_message

Store messages in conversation history

get_conversation_history

Retrieve past conversations

search_conversation_by_keywords

Search conversations by keywords

summarize_conversation

AI-powered conversation summarization

store_context

Store dynamic contextual data

get_context

Retrieve stored context

get_all_contexts

Get all contexts for an agent

search_context_by_keywords

Keyword search in contexts

prune_old_context

Clean up old context entries

summarize_context

AI summarization of context

extract_entities

Extract entities from context

semantic_search_context

Vector-based semantic search

create_task_plan

Create plans (manual or AI-generated)

get_task_plan_details

Get detailed plan information

list_task_plans

List all plans

update_task_plan_status

Update plan status

delete_task_plan

Remove plans

ai_analyze_plan

AI analysis of plan quality

ai_suggest_subtasks

AI-generated subtask suggestions

ai_suggest_task_details

AI-enhanced task details

ai_summarize_task_progress

AI progress summaries

knowledge_graph_memory

Comprehensive KG operations

tavily_web_search

Advanced web search

ask_gemini

Direct Gemini AI queries

analyze_code_file_with_gemini

AI code analysis

refine_user_prompt

AI prompt enhancement

ingest_codebase_embeddings

Vector embedding generation

The server provides 65+ tools organized into categories:

<details>
<summary><b>Conversation Management (4 tools)</b></summary>

- store_conversation_message - Store messages in conversation history
- get_conversation_history - Retrieve past conversations
- search_conversation_by_keywords - Search conversations by keywords
- summarize_conversation - AI-powered conversation summarization

</details>

<details>
<summary><b>Context Management (9 tools)</b></summary>

- store_context - Store dynamic contextual data
- get_context - Retrieve stored context
- get_all_contexts - Get all contexts for an agent
- search_context_by_keywords - Keyword search in contexts
- prune_old_context - Clean up old context entries
- summarize_context - AI summarization of context
- extract_entities - Extract entities from context
- semantic_search_context - Vector-based semantic search

</details>

<details>
<summary><b>Plan Management (15 tools)</b></summary>

- create_task_plan - Create plans (manual or AI-generated)
- get_task_plan_details - Get detailed plan information
- list_task_plans - List all plans
- update_task_plan_status - Update plan status
- delete_task_plan - Remove plans
- ai_analyze_plan - AI analysis of plan quality
- ai_suggest_subtasks - AI-generated subtask suggestions
- ai_suggest_task_details - AI-enhanced task details
- ai_summarize_task_progress - AI progress summaries

</details>

<details>
<summary><b>Knowledge Graph (9 operations)</b></summary>

- knowledge_graph_memory - Comprehensive KG operations
- Create/read/update/delete entities
- Manage relationships
- Add observations
- Natural language queries
- Infer relationships
- Generate visualizations

</details>

<details>
<summary><b>Comprehensive Logging (23 tools)</b></summary>

- Tool execution logging
- Task progress tracking
- Error logging and management
- Correction tracking
- Success metrics
- Review logs (task and plan level)

</details>

<details>
<summary><b>Git Operations (16 tools)</b></summary>

- Complete Git workflow support
- Clone, pull, push, commit
- Branch management
- Stash operations
- Remote management

</details>

<details>
<summary><b>External Services (5 tools)</b></summary>

- tavily_web_search - Advanced web search
- ask_gemini - Direct Gemini AI queries
- analyze_code_file_with_gemini - AI code analysis
- refine_user_prompt - AI prompt enhancement
- ingest_codebase_embeddings - Vector embedding generation

</details>

---

<div align="center">

Memory MCP Server
License: MIT
Node.js
TypeScript

๐Ÿš€ Your AI Agent's Persistent Brain - A Comprehensive Memory & Task Management System

Features โ€ข Installation โ€ข Configuration โ€ข Workflow โ€ข Tools โ€ข Architecture โ€ข Development

</div>

---

> ### ๐Ÿšจ CRITICAL: This MCP Server requires workflow.md to function properly!
>
> The workflow.md file is not optional - it's the AI Driver that transforms this collection of tools into an intelligent system. Without it, your AI agent will have tools but no structured way to use them effectively.
>
> Before using this server:
> 1. โœ… Install and configure the MCP server
> 2. โœ… Load workflow.md into your AI agent's system prompt
> 3. โœ… Ensure your agent follows the 6-mode operational structure
>
> ๐Ÿ“– Jump to workflow.md documentation

---

๐Ÿ“‹ Table of Contents

- ๐ŸŒŸ Overview
- โœจ Features
- ๐Ÿš€ Installation
- โš™๏ธ Configuration
- ๐ŸŽฎ The AI Driver: Understanding workflow.md
- ๐Ÿ› ๏ธ Available Tools
- ๐Ÿ—๏ธ Architecture
- ๐Ÿ’ป Development
- ๐Ÿ“š Documentation
- ๐Ÿค Contributing
- ๐Ÿ“„ License

---

๐ŸŒŸ Overview

The Memory MCP Server (Orchestrator) is a powerful Model Context Protocol (MCP) server that provides AI agents with persistent memory, advanced task planning, and comprehensive knowledge management capabilities. Built with TypeScript and SQLite, it transforms your AI agents from stateless assistants into intelligent systems with long-term memory and structured workflows.

๐Ÿšจ Critical Component: The AI Driver (workflow.md)

The workflow.md file is the brain of this system! It contains the operational protocols and behavioral rules that transform a collection of tools into an intelligent, coordinated system. Think of it as the "AI Driver" that:

- ๐ŸŽฏ Defines 6 Operational Modes: From prompt refinement to task execution
- ๐Ÿ›ก๏ธ Enforces Safety Protocols: Prevents unauthorized actions and overager behavior
- ๐Ÿ“‹ Structures Workflows: Ensures systematic approach to every task
- ๐Ÿ”„ Manages State Transitions: Controls how the AI moves between different modes
- โœ… Validates Actions: Requires user approval before executing changes

Without workflow.md, this is just a toolbox. With it, it becomes an intelligent agent system.

๐ŸŽฏ Key Benefits

- ๐Ÿง  Persistent Memory: Never lose context between sessions
- ๐Ÿ“Š Structured Planning: Break complex tasks into manageable steps
- ๐Ÿ” Knowledge Graph: Build and query relationships between entities
- ๐Ÿค– AI-Enhanced: Leverage Gemini AI for intelligent task suggestions
- ๐Ÿ“ˆ Performance Tracking: Monitor success metrics and learn from corrections
- ๐Ÿ”— External Integrations: Connect with web search and AI services

---

โœจ Features

๐Ÿ’พ Memory Management

- Conversation History: Track multi-turn dialogues with full context - Dynamic Context Storage: Version-controlled storage for agent state, preferences, and parameters - Knowledge Graph: Create, query, and manage entity relationships - Vector Embeddings: Semantic search capabilities for code and documentation

๐Ÿ“ Task & Planning System

- AI-Powered Planning: Generate comprehensive plans from refined prompts - Hierarchical Tasks: Support for tasks, subtasks, and dependencies - Progress Tracking: Real-time monitoring of task execution - Review System: Built-in task and plan review mechanisms

๐Ÿค– AI Integration

- Google Gemini Integration: - Prompt refinement and structuring - Context summarization - Entity extraction - Code analysis - Task suggestions - Tavily Web Search: Advanced web search capabilities - Semantic Search: Vector-based content retrieval

๐Ÿ›ก๏ธ Reliability & Compliance

- Data Validation: JSON schema validation for all inputs - Comprehensive Logging: Track all operations and errors - Backup & Restore: Full database backup capabilities - MCP Compliant: Seamless integration with MCP-compatible clients

---

๐Ÿš€ Installation

Prerequisites

<div align="center">

| Requirement | Version | Required |
|------------|---------|----------|
| Node.js | 18.x or higher | โœ… |
| npm | Latest | โœ… |
| Git | Any | โœ… |

</div>

Step-by-Step Installation

```bash

No reviews yet โ€” be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.