Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Productivity
  4. /
  5. Memory MCP Server
Productivity
Memory MCP Server icon

Memory MCP Server

by Model Context Protocol

A reference MCP server that gives an assistant persistent memory by storing a local knowledge graph of entities, relations and observations.

Plugin·MCP server·Free

View on GitHub(opens in a new tab)

About Memory MCP Server

Key features of Memory MCP Server

  • Entities with names, types and observations
  • Directed relations stored in active voice
  • Tools to create, add and delete entities, relations and observations
  • read_graph, search_nodes and open_nodes for retrieval
  • Knowledge graph exposed as an MCP resource with update notifications
  • Custom storage path through MEMORY_FILE_PATH
  • Lock file for sharing one memory file between clients
  • Runs through npx or Docker

Who Memory MCP Server is for

  • Users who want an assistant to remember details across chats
  • Developers building memory into MCP clients
  • Claude Desktop and VS Code users
  • People learning how MCP servers are built

How to use Memory MCP Server

  1. 1

    Step 1: Make sure Node.js 24 or later is installed if you run it through npx.

  2. 2

    Step 2: Add a memory entry to claude_desktop_config.json using npx with -y @modelcontextprotocol/server-memory, or the Docker command from the README.

  3. 3

    Step 3: Optionally set MEMORY_FILE_PATH to choose where the memory file is stored.

  4. 4

    Step 4: Add a system prompt, for example in a Claude.ai Project, telling the model when to retrieve and record memory.

  5. 5

    Step 5: Chat as usual; the model can then create entities and search the graph.

Memory MCP Server FAQ

Where is the memory stored?

In a local JSONL file, memory.jsonl in the server directory by default. Set MEMORY_FILE_PATH to use another path.

Can two clients share one memory?

Yes. Write tools use an exclusive lock file so writes from different processes take turns. This is not safe on a network filesystem that does not honour exclusive file creation.

How does the model know when to save memories?

That depends on your prompt. The README gives an example system prompt, and notes that changing it changes how often and what kinds of memories are created.

Tools

9
  • create_entitiesCreate multiple entities in the knowledge graph.
  • create_relations
  • add_observations
  • delete_entities
  • delete_observationsDelete selected observations from entities.
  • delete_relationsDelete selected relations.
  • read_graphRead the complete knowledge graph.
  • search_nodesSearch entity names, types, and observation content.
  • open_nodesRetrieve specific nodes by name.

Prompts and resources

Resources 1

  • knowledge-graphFull persistent knowledge graph containing entities and relations.

Technical details

Requirements

  • An MCP-compatible client/host and the runtime required by the selected package (Node.js for npm servers or Python/uv for Python servers).

Details

Pricing
Free
Type
Plugin · MCP server
Platforms
  • MCP
Hosting
Remote
Categories
ProductivityAIData
Added
Sep 17, 2026
Model Context Protocol iconPublisherModel Context ProtocolModel Context Protocol (MCP) is an open protocol and open-source project for connecting AI applications to external tools, data sources, and services. This organization row groups the official reference MCP servers maintained in the modelcontextprotocol/servers repository.

Built from public sources

We put this page together from Memory MCP Server’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with Memory MCP Server.

Work at Memory MCP Server? Claim the listing to manage it yourself.

Something wrong here?

More from Model Context Protocol

View publisher
Git MCP Server iconGit MCP ServerModel Context Protocol · FreeOfficial MCP reference server for inspecting and manipulating Git repositories through status, diff, log, show, staging, commit, branch, and checkout tools.Developer Tools · FreeFilesystem MCP Server iconFilesystem MCP ServerModel Context Protocol · FreeA Node.js MCP server that lets an AI client read, write, search and manage files, limited to directories you allow. It is published on npm as @modelcontextprotocol/server-filesystem.Developer Tools · FreeSequential Thinking MCP Server iconSequential Thinking MCP ServerModel Context Protocol · FreeA reference MCP server with one tool, sequential_thinking, that helps a model work through a problem as a series of steps it can revise or branch.Productivity · Free

Related tools

See more
M3 Memory MCP iconM3 Memory MCPskynetcmd · Contact for pricingm3 Memory is a local-first memory layer that lets AI coding assistants keep facts, decisions and conversation history across sessions and tools. Assistants reach it through MCP, and it also has a command-line interface.Productivity · Contact for pricingInspeximus MCP iconInspeximus MCPDanceNitra · Contact for pricingInspeximus is tamper-evident long-term memory for AI agents, shipped as one zero-dependency Python file plus an MCP server. A corrected fact stays corrected, and erasures can be proven.Productivity · Contact for pricingSMSage MCPl33tdawg · Contact for pricingSAGE is a governed memory layer for AI agents. Each memory is signed by an agent, admitted through a review step, limited by permissions and kept with an audit trail.Productivity · Contact for pricing