Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-external-memory remember that the deployment is scheduled for Friday 3pm"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that gives LLMs persistent, searchable semantic memory.
pip install mcp-external-memoryRelated MCP server: Recall
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")mcp-external-memory --helpTool | Description |
| Persist text + optional namespace/tags/metadata |
| Semantic search (cosine similarity) over all memories |
| Retrieve a single memory by ID |
| Delete a memory by ID |
| List memories with optional namespace/tag filter + pagination |
| Count of memories, namespaces, DB path |
| Update an existing memory |
The server supports multiple embedding backends:
TF-IDF (default): Pure Python, no external dependencies
OpenAI: Uses text-embedding-3-small model
Ollama: Local embeddings with Ollama
Set via MEMORY_EMBED_BACKEND environment variable.
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-name: io.github.daedalus/mcp-external-memory
This server cannot be deployed
Memory system for AI agents with semantic search. Store and recall memories with ease.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
Persistent memory for AI agents. Search, store, and recall across sessions.
