memory-mcp

by jamesanz

Not rated
GitHub

About

A simple MCP server that stores and retrieves memories from multiple LLMs.

Details

Author
jamesanz
Categories
Database

Setup

Install memory-mcp in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/jamesanz/memory-mcp

Follow the installation instructions in the repository README, then restart your MCP client.

Persistent memory and context window caching for LLM conversations.Save, retrieve, and manage memories with intelligent context archiving. MongoDB-backed storage.

AnMCP (Model Context Protocol)server that provides memory management and context window caching for AI coding environments like Cursor and Claude Desktop.

- πŸ’ΎPersistent Storage– MongoDB-backed memory that survives sessions
- 🧠Context Caching– Intelligent archiving and retrieval of conversation context
- 🏷️Tag-based Search– Organize and find memories by tags
- πŸ“ŠRelevance Scoring– Automatically score archived content relevance
- ⚑Easy Setup– One-click install in Cursor or simple manual setup

Ready to add memory to your AI workflow? Install in seconds:

npm install -g @jamesanz/memory-mcp # Or from source: git clone https://github.com/JamesANZ/memory-mcp.git cd memory-mcp && npm install && npm run build

- save-memories– Save memories to database (overwrites existing)
- get-memories– Retrieve all stored memories
- add-memories– Append new memories without overwriting
- clear-memories– Remove all stored memories

- archive-context– Archive conversation context with tags
- retrieve-context– Retrieve relevant archived context
- score-relevance– Score archived content relevance
- create-summary– Create summaries of archived content
- get-conversation-summaries– Get all summaries for a conversation
- search-context-by-tags– Search archived content by tags

cursor://anysphere.cursor-deeplink/mcp/install?name=memory-mcp&config=eyJtZW1vcnktbWNwIjp7ImNvbW1hbmQiOiJucHgiLCJhcmdzIjpbIi15IiwiQGphbWVzYW56L21lbW9yeS1tY3AiXX19
# Clone and build git clone https://github.com/JamesANZ/memory-mcp.git cd memory-mcp npm install npm run build # Set MongoDB connection string export MONGODB_URI="mongodb://localhost:27017" # Run server npm start

macOS:~/Library/Application Support/Claude/claude_desktop_config.json
Windows:%APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "memory-mcp": { "command": "node", "args": ["/absolute/path/to/memory-mcp/build/index.js"], "env": { "MONGODB_URI": "mongodb://localhost:27017" } } } }

Restart Claude Desktop after configuration.

export MONGODB_URI="mongodb://localhost:27017"
{ "tool": "save-memories", "arguments": { "memories": ["User prefers TypeScript", "User works on blockchain projects"], "llm": "claude", "userId": "user123" } }
{ "tool": "get-memories", "arguments": {} }

Archive conversation context when it gets too long:

{ "tool": "archive-context", "arguments": { "conversationId": "conv-123", "contextMessages": ["Message 1", "Message 2"], "tags": ["coding", "typescript"], "llm": "claude" } }

Get archived content relevant to current conversation:

{ "tool": "retrieve-context", "arguments": { "conversationId": "conv-123", "tags": ["coding"], "minRelevanceScore": 0.5, "limit": 10 } }

- Archives contentwhen context usage reaches 80%
- Retrieves relevant contentwhen usage drops below 30%
- Scores relevanceusing keyword overlap
- Creates summariesto condense long conversations

- Long Conversations– Manage context windows for extended sessions
- Memory Persistence– Save important information across sessions
- Context Retrieval– Bring back relevant past conversations
- Research Projects– Organize and tag research conversations

Built with:Node.js, TypeScript, MCP SDK, MongoDB
Dependencies:@modelcontextprotocol/sdk,mongodb,zod
Platforms:macOS, Windows, Linux

Storage:MongoDB (default:mongodb://localhost:27017)

⭐If this project helps you, please star it on GitHub!⭐

Contributions welcome! Please open an issue or submit a pull request.

If you find this project useful, consider supporting it:

lnbc1pjhhsqepp5mjgwnvg0z53shm22hfe9us289lnaqkwv8rn2s0rtekg5vvj56xnqdqqcqzzsxqyz5vqsp5gu6vh9hyp94c7t3tkpqrp2r059t4vrw7ps78a4n0a2u52678c7yq9qyyssq7zcferywka50wcy75skjfrdrk930cuyx24rg55cwfuzxs49rc9c53mpz6zug5y2544pt8y9jflnq0ltlha26ed846jh0y7n4gm8jd3qqaautqa

β‚Ώ Bitcoin:bc1ptzvr93pn959xq4et6sqzpfnkk2args22ewv5u2th4ps7hshfaqrshe0xtp

Ξ Ethereum/EVM:0x42ea529282DDE0AA87B42d9E83316eb23FE62c3f

Official Airtable MCP server and skills for working with bases, records, workflows, and business operations from AI agents.

MCP Server For Apache Doris, an MPP-based real-time data warehouse.

Official MCP Server from Atlan which enables you to bring the power of metadata to your AI tools

Query Onchain data, like ERC20 tokens, transaction history, smart contract state.

Read and write access to your Baserow tables.

Introspect and query your apps deployed to Convex.

Interact with the data stored in Couchbase clusters using natural language.

Maritime intelligence for tracking vessels, analysing ports, and exploring ship data.

No reviews yet β€” 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.