Kiro MCP Memory

v1.0.0Knowledge & Memorystable

An enhanced MCP (Model Context Protocol) server for intelligent memory and task management, designed for AI assistants and development workflows. Features semantic search, automatic task extraction, knowledge graphs, and comprehensive project managem

clinekirokiro-mcp-memorymcp-memorymcp-server
Share:
33
Stars
0
Downloads
0
Weekly
0/5

What is Kiro MCP Memory?

Kiro MCP Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enhanced mcp (model context protocol) server for intelligent memory and task management, designed for ai assistants and development workflows. features semantic search, automatic task extraction, know...

An enhanced MCP (Model Context Protocol) server for intelligent memory and task management, designed for AI assistants and development workflows. Features semantic search, automatic task extraction, knowledge graphs, and comprehensive project managem

This server falls under the Knowledge & Memory and Coding Agents categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An enhanced MCP (Model Context Protocol) server for intellig

Use Cases

Maintain semantic memory for AI assistants and coding tools.
Track tasks automatically with knowledge graphs.
Search and manage project information across workflows.
cbunting99

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedApr 26, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx kiro-mcp-memory

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Kiro MCP Memory

Kiro MCP Memory (enhanced-mcp-memory) is a full-featured memory and task management MCP server designed for AI coding assistants like Cline, Roo Code, and VS Code-based agents. It provides semantic search over stored memories using sentence-transformers embeddings, automatic task extraction from conversations, structured sequential thinking chains, knowledge graph relationships, and project convention learning that detects your OS, shell, package manager, and build system to prevent incorrect command suggestions. Developers use it to give their AI assistant persistent, searchable context across sessions without re-explaining the project every time.

Prerequisites

  • Python 3.8 or higher installed
  • uv installed for the recommended uvx installation: 'curl -LsSf https://astral.sh/uv/install.sh | sh'
  • Approximately 90 MB of disk space for the sentence-transformers model (downloaded automatically on first run)
  • Cline, Roo Code, Claude Desktop, or another MCP-compatible client
1

Install enhanced-mcp-memory via uvx (recommended)

uvx runs the package directly from PyPI without a permanent global install. This is the fastest way to get started.

uvx enhanced-mcp-memory
2

Alternative: install with pip

For a permanent installation you can reference by executable name, install with pip.

git clone https://github.com/cbunting99/enhanced-mcp-memory.git
cd enhanced-mcp-memory
pip install -e .
3

Configure your MCP client

Add the server to your client config with environment variables controlling memory limits, log level, and storage location.

4

Wait for the sentence-transformers model to download on first run

On the first startup, the server downloads a ~90 MB sentence-transformers model for semantic search. Subsequent starts use the cached model. Check the logs directory for progress if startup seems slow.

5

Auto-learn your project conventions

Ask the AI to run the auto_learn_project_conventions tool on your project directory. The server will detect your OS, package manager, build tools, and scripts, storing them as high-importance memories.

Kiro MCP Memory Examples

Client configuration

Add this to your cline_mcp_settings.json or claude_desktop_config.json. DATA_DIR controls where the SQLite database and logs are stored.

{
  "mcpServers": {
    "memory-manager": {
      "command": "uvx",
      "args": ["enhanced-mcp-memory"],
      "env": {
        "LOG_LEVEL": "INFO",
        "MAX_MEMORY_ITEMS": "1000",
        "ENABLE_AUTO_CLEANUP": "true",
        "DATA_DIR": "~/ClaudeMemory"
      }
    }
  }
}

Prompts to try

Use these prompts with Cline or Claude to exercise memory storage, semantic search, task management, and convention learning.

- "Learn the project conventions for /Users/me/projects/myapp"
- "What do you remember about the database schema for this project?"
- "Create a task: refactor the authentication module, priority high"
- "What tasks are currently in progress?"
- "Give me a project summary"
- "Start a thinking chain to plan the migration from REST to GraphQL"
- "Consolidate the current session so I can hand off to a new chat"

Troubleshooting Kiro MCP Memory

Slow startup on first run (30-60 seconds)

The sentence-transformers model (~90 MB) is being downloaded on first run. This is a one-time operation. Subsequent starts will be fast because the model is cached locally.

Semantic search returns unrelated memories

The similarity threshold may be too loose for your use case. Try more specific natural language queries in get_memory_context. You can also run optimize_memories to remove duplicates and improve retrieval quality.

Data directory not found or permission denied on DATA_DIR

Ensure the directory specified in DATA_DIR exists and is writable by the process running the MCP server. The default ~/ClaudeMemory is created automatically, but a custom path must exist beforehand. On Windows, use a full absolute path rather than a tilde-expanded path.

Frequently Asked Questions about Kiro MCP Memory

What is Kiro MCP Memory?

Kiro MCP Memory is a Model Context Protocol (MCP) server that enhanced mcp (model context protocol) server for intelligent memory and task management, designed for ai assistants and development workflows. features semantic search, automatic task extraction, knowledge graphs, and comprehensive project managem It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Kiro MCP Memory?

Follow the installation instructions on the Kiro MCP Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Kiro MCP Memory?

Kiro MCP Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Kiro MCP Memory free to use?

Yes, Kiro MCP Memory is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "kiro-mcp-memory": { "command": "npx", "args": ["-y", "kiro-mcp-memory"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Kiro MCP Memory?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides