Summary
Gives Claude persistent memory through semantic search over stored text snippets. Exposes seven tools: memory_store for saving content with optional namespaces and tags, memory_search for cosine similarity lookups, plus get, delete, list, update, and stats operations. Supports three embedding backends out of the box: TF-IDF with no dependencies, OpenAI's text-embedding-3-small, or local Ollama models. Reach for this when you need Claude to remember user preferences, project context, or domain knowledge across conversations. Stores everything in a local database that persists between sessions. Install via pip, configure the embedding backend through environment variables, and start storing queryable memories immediately.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
mcp-external-memory
An MCP server that gives LLMs persistent, searchable semantic memory.
Install
pip install mcp-external-memory
Usage
from mcp_external_memory import memory_store, memory_search
# Store a memory
result = memory_store(content="Alice prefers dark mode", namespace="users", tags=["alice", "ui"])
# Search memories
results = memory_search(query="what does Alice prefer?", namespace="users")
CLI
mcp-external-memory --help
API
Tools
| Tool | Description |
|---|---|
memory_store | Persist text + optional namespace/tags/metadata |
memory_search | Semantic search (cosine similarity) over all memories |
memory_get | Retrieve a single memory by ID |
memory_delete | Delete a memory by ID |
memory_list | List memories with optional namespace/tag filter + pagination |
memory_stats | Count of memories, namespaces, DB path |
memory_update | Update an existing memory |
Embedding Backends
The server supports multiple embedding backends:
- TF-IDF (default): Pure Python, no external dependencies
- OpenAI: Uses
text-embedding-3-smallmodel - Ollama: Local embeddings with Ollama
Set via MEMORY_EMBED_BACKEND environment variable.
Development
git clone https://github.com/daedalus/mcp-external-memory.git
cd mcp-external-memory
pip install -e ".[test]"
# run tests
pytest
# format
ruff format src/ tests/
# lint
ruff check src/ tests/
# type check
mypy src/
MCP Registry
mcp-name: io.github.daedalus/mcp-external-memory
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Categories
Registryactive
Packagemcp-external-memory
TransportSTDIO
UpdatedApr 13, 2026
