SkillFoxx

mcp-memory-ydb

An official long-term memory MCP server for agents on YDB Serverless: mem0 extracts facts, YDB stores the vectors

  • 2 ★ on the repository
  • Last commit
  • Apache-2.0
MCP serverOfficial

Extended access

Why this level

  • Stores extracted facts about the user in a YDB database readable by anyone with access to that database
  • Sends text to a third-party LLM provider for fact extraction and embeddings
All reasons and checks
Russian stack

ydb-platform/mcp-memory-ydbAuthor:YDB

Install

Services

Manual install

uvx mcp-memory-ydb setup

The README's setup wizard: creates .mcp-memory-ydb.env and prints ready connection commands.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Stores extracted facts about the user in a YDB database readable by anyone with access to that database
  • Sends text to a third-party LLM provider for fact extraction and embeddings

This is third-party code. Review the repository files before installing.

What it does

The server is built on ydb-mcp, Yandex's own official MCP server for YDB, with the generic SQL tools switched off and four memory tools in their place: memory_search does a semantic lookup over facts, memory_save hands text to mem0, which uses an LLM to extract facts and append them (facts are not auto-overwritten, only accumulated), and memory_delete / memory_update edit a specific fact by its id. All memory lives in YDB Serverless as a vector store via langchain-ydb, and fact extraction plus embeddings work with any OpenAI-compatible provider, OpenAI, YandexGPT or local Ollama.

Who it is for. For agent developers who want cross-session long-term memory on their own YDB infrastructure rather than a third-party cloud.

Good fit when

  • You need agent memory that survives a session restart, built on YDB
  • You already have, or are willing to set up, YDB Serverless with a service account holding the ydb.editor role
  • You want facts stored in Russian without being translated to English

Not a fit when

  • You have no access to YDB Serverless or an OpenAI-compatible LLM for fact extraction
  • You need multi-tenant memory with access control: a namespace is a query filter, not a security boundary

Example request

Remember that my favorite language is Rust and I work in the Moscow timezone

MCP

Transport
stdio
Authentication
API key

Environment variables

YDB_ENDPOINT required
The YDB Serverless endpoint, e.g. grpcs://ydb.serverless.yandexcloud.net:2135.
YDB_DATABASE required
The database path, /ru-central1/<folder>/<db>.
YDB_SA_KEY_FILE secret
Path to the service account's JSON key with the ydb.editor role.
LLM_API_KEY required, secret
API key for an OpenAI-compatible provider (OpenAI, Yandex Cloud, Ollama) used for fact extraction and embeddings.

Limitations

mem0 2.x is append-only: it does not auto-delete or merge facts, stale facts need manual cleanup via memory_delete/update. A namespace is not a security boundary: anything with access to the YDB database can read every namespace. By default extracted facts are stored in English; for Russian you need to set MEMORY_FACT_INSTRUCTIONS in Russian.

How to disable. Run claude mcp remove memory-ydb, or remove the memory-ydb entry from your MCP client config.

FAQ

Do I need to call memory_search and memory_save by hand?

No, the server ships built-in MCP instructions, and clients like Claude Code call them automatically before and after answering.

Can I use YandexGPT instead of OpenAI for embeddings?

Yes, any OpenAI-compatible provider works, including Yandex Cloud.

Discussion

No questions or reviews yet.

All YDB tools
Official

YDB's own official MCP server from the database's developers: parameterized SQL queries, execution plans, directory browsing, and a base for custom servers

MCP serverBroad access29

YDB MCP connection demo built on a notes app

Simple CLI Notes Application with YDB

Official

An official YDB example: docker compose brings up a YDB database and the ydb-mcp server, and Cursor runs SQL through them right from chat

MCP serverExtended access
Russian stack

A skill and MCP server for operating Docker-based local-ydb deployments: nodes, schema, dump and restore, locally or over SSH

PluginExtended access5
Russian stack

An unofficial single-file MCP server for Yandex Object Storage: bucket listing, contents and file downloads via the AWS SDK

MCP serverExtended access1
Russian stack

MCP server for the Yandex DataLens public API: 70 tools for dashboards, charts, datasets and connections

MCP serverExtended access8

A local MCP server that turns a folder of documents into a knowledge base with hybrid search for Claude Code and Cursor

MCP serverExtended access305

README in short

The README explains the memory model in detail (mem0 extracts facts, langchain-ydb stores the vectors, YDB Serverless is the database), gives a uvx mcp-memory-ydb setup wizard, connection instructions for Claude Code, Cursor and VS Code, a section explaining that a namespace is a partition label rather than a security boundary, and a troubleshooting section for common YDB connection errors.

README badge

Report a problem