memory_storeLABSCO SUMMARY
Memory with entity resolution, so a vague reference two weeks later still lands.
Most memory servers store text and search it. The part that matters here is entity_resolve and context_inject working together: you say 'that project', and the pronoun is resolved to a named thing before the search runs.
What it is
A memory server backed by Azure Cosmos DB and OpenAI embeddings. It stores what you discuss, extracts the people, companies and projects mentioned, and pulls the relevant pieces back when a later question refers to them.
What you get
- memory_store — save information with the entities pulled out of it automatically
- memory_search — semantic search across everything stored
- context_inject — fetch the context relevant to the question being asked right now
- entity_resolve — turn 'he' or 'that company' into the actual person or company
- conversation_analyze — patterns across your discussions
- memory_timeline — when a given entity came up, in order
Requirements
Node.js 18+, an Azure Cosmos DB account and an OpenAI API key. Cosmos endpoint, key, database and container names go in the environment, along with OPENAI_API_KEY. Built from source and run as a node process.
Setup effort
Build from source — git clone https://github.com/PlumyCat/mcp-memory-server.git
USE CASES
01
Picking up a debugging thread weeks later
Ask what the problem was and the earlier discussion comes back with the service and symptom attached, without you naming either.
02
Resolving who or what you just referred to
Pronouns and vague noun phrases get mapped to entities already stored, with a confidence score attached.
03
Seeing when a topic came up and how often
Get a timeline of every mention of one company or project, and statistics across your discussions.
04
Keeping search results you already paid for
Findings from earlier lookups are stored with the rest, so re-asking pulls from memory rather than searching again.
6 tools
Listed in project docs. Your client may show a different list.
memory_searchcontext_injectentity_resolveconversation_analyzememory_timelineBEFORE YOU INSTALL
What to know first
Tools you get
6 tools named in the project's documentation.
Requires
- Node.js 18+
- COSMOS_KEY in your environment
- OPENAI_API_KEY in your environment
- COSMOS_ENDPOINT in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/PlumyCat/mcp-memory-server.git
cd mcp-memory-server
npm install
npm run build
cp .env.example .envMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"memory": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MCP_MEMORY_SERVER>/dist/index.js"
],
"cwd": "<YOUR_PATH_TO_MCP_MEMORY_SERVER>"
}
}
}COSMOS_ENDPOINT, COSMOS_KEY and OPENAI_API_KEY go in the .env file the last step creates. The server reads that file from the repository folder, so the client configuration does not set them.
