OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Memento MCP

Memento MCP is a TypeScript Model Context Protocol server that gives compatible LLM clients persistent knowledge-graph memory using Neo4j for graph storage and vector search.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Memento MCP — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Memento MCP when an MCP-compatible LLM client needs persistent, structured memory backed by a Neo4j graph and vector search.

Who it is for

  • Developers connecting persistent memory to MCP-compatible LLM clients.
  • Teams that want to store entities, observations and relationships with semantic retrieval and version history.

Documented uses

  • Add persistent knowledge-graph memory to an MCP-compatible client such as Claude Desktop, Cursor or GitHub Copilot.
  • Retrieve related entities by semantic similarity as well as stored graph relationships.
  • Represent changing facts and relationships with version histories and temporal confidence decay.
Before you choose

Requirements & limits

  • Neo4j 5.13 or later is required for vector search.
  • Semantic search uses OpenAI embeddings; an OpenAI API key is needed for real embeddings.
  • Neo4j Desktop and Docker Compose are the setup approaches described in the repository documentation.
  • The repository lists an MIT license and TypeScript as its primary language.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare Neo4j for Memento MCP

Set up a Neo4j database that Memento MCP can use for graph storage and vector search.

Before you start

  • Neo4j 5.13 or later.
  • Neo4j Desktop, or Docker Compose for the documented container setup.

Steps

  1. In Neo4j Desktop, create a project and add a database, or use the repository's Docker Compose setup for Neo4j.

  2. Set the database password and start the database.

  3. Configure Memento MCP's Neo4j URI, username, password and database name to match the running database.

Expected outcome

A configured Neo4j database connection for Memento MCP; the documentation says schema initialization occurs automatically on connection during normal operation.

Guide limitations

  • This covers database preparation and connection settings, not configuring or launching an MCP client.
  • Semantic search also requires OpenAI embedding credentials for real embeddings.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Memento MCPAdd persistent knowledge-graph memory to an MCP-compatible client such as Claude Desktop, Cursor or GitHub Copilot.Cloud, Self-hosted, Server
KektordbSave and retrieve semantic memories across agent sessions.Self-hosted, ServerThe README describes self-hosted use and displays an Apache 2.0 license badge.
LongbowStore and retrieve dense or sparse vectors with HNSW search.Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
gannonh/memento-mcp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction