About mcp-external-memory
mcp-external-memory is an MCP server for LLMs that stores and searches persistent text memories. It supports namespaces and tags, with TF-IDF, OpenAI, and Ollama embedding backends.
Key features
- 01Store, update, and delete memories
- 02Semantic search by query
- 03Retrieve or list memories
- 04Filter by namespace and tag
- 05TF-IDF, OpenAI, and Ollama embeddings
Use cases
- 01Save user preferences for later retrieval
- 02Search stored notes by meaning
- 03Organize memories by namespace or tag
MCP support
Exposes tools to store, search, retrieve, list, update, and delete memories, as well as inspect memory statistics.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.