MCP.so
Sign In

Simple Memory Extension MCP Server

@gmacev

About Simple Memory Extension MCP Server

An MCP server to extend the context of agents. Useful when coding big features or vibe coding and need to store/recall progress, key moments or changes or anything worth remembering. Simply ask the agent to store memories and recall whenever you want.

Basic information

Category

Memory & Knowledge

License

MIT

Runtime

node

Transports

stdio

Publisher

gmacev

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "simple-memory": {
      "type": "http",
      "url": "http://localhost:3000/sse"
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Simple Memory Extension MCP Server?

An MCP server that extends the context window / memory of AI agents by letting them store and recall progress, key moments, changes, or any noteworthy information. It is designed for developers working on large features or “vibe coding” who need persistent memory across sessions.

How to use Simple Memory Extension MCP Server?

Install with npm install, then start with npm start. Configure the MCP client by adding "simple-memory" to mcpServers with "url": "http://localhost:3000/sse" and "trust": false. Set environment variables like DB_PATH, PORT, USE_HTTP_SSE, and LOG_LEVEL in a .env file. Use the provided tools to store, retrieve, delete context items, manage namespaces, and perform semantic searches.

Key features of Simple Memory Extension MCP Server

  • Store key-value pairs within named namespaces
  • Retrieve items by exact key or by semantic search
  • Create, delete, and list namespaces
  • Semantic search using E5 embedding model
  • SQLite database for persistent storage

Use cases of Simple Memory Extension MCP Server

  • Remember coding progress and decisions during large feature work
  • Let the agent manage its own memory via Cursor rules
  • Recall specific changes or key moments from past sessions
  • Find context items by meaning rather than by key name

FAQ from Simple Memory Extension MCP Server

What database does the server use?

It uses SQLite, with the database file path configured via the DB_PATH environment variable (default ./data/context.db).

How does semantic search work?

Queries are converted to vectors using the E5 embedding model (intfloat/multilingual-e5-large-instruct). Text is chunked for better matching, cosine similarity is computed, results are filtered by a threshold and sorted by similarity, and the top matches are returned.

Does it require Python?

Yes. The semantic search feature requires Python dependencies, which are automatically installed when you run npm start.

What transport protocols are supported?

The server supports HTTP SSE (Server‑Sent Events) by default (USE_HTTP_SSE=true). It also supports stdio when USE_HTTP_SSE=false.

How do I set up the server in my MCP client?

Add a "simple-memory" entry to mcpServers with "url": "http://localhost:3000/sse" and "trust": false. Adjust the port if you change the PORT environment variable.

Comments

More Memory & Knowledge MCP servers