AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Memory & Context/
mcp-memory-service
mcp-memory-service logo

mcp-memory-service

Active·★ 2.1k·Apache-2.0·Updated 2026-10-27
★ Essential★ Trending

MCP Memory Service gives AI assistants memory that survives new chat sessions. The README's pitch is that you stop re-explaining your project: it captures project context, architecture decisions and code patterns, and a fresh session can recall them. It works with any MCP-compatible client, and the README names Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Aider, Zed, Continue and many others. The feature list covers OAuth and team collaboration, a document ingestion system, memory consolidation, a memory type ontology and a dashboard.

Install with `pip install mcp-memory-service`, then either run the quick installer (`python -m mcp_memory_service.scripts.installation.install --quick`) to configure Claude Desktop with a SQLite backend, or add a `memory server` entry to your MCP config by hand. For production or team use you can clone the repo and run the installer to pick SQLite (local, single user), Cloudflare (cloud, multi-device sync) or a hybrid of the two. The README also says it is compatible with the SHODH unified memory API specification and carries notes on Python 3.13 and macOS SQLite extension support. It is Apache licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-25.

License
Apache-2.0
Latest release
v12.3.1 · 2026-10-23
Last commit
2026-10-25
Contributors
136
Forks
365
Open issues and PRs
28
First published
2024-12-26
PyPI package
mcp-memory-service 12.3.1 · 2,747 downloads last week

Source: GitHub, npm and PyPI public APIs.

#AI Memory#Context Management#Developer Tools#MCP#Python#Coding
$ Install
$ pip install mcp-memory-service
↗ Visit site★ GitHub
01

Features

01Persistent Memory
02Smart Retrieval
03Multi-Client Compatibility
04Cloud Sync (Optional)
05Web Dashboard
02

Why choose it

+Memory persists across sessions, so new chats do not start from zero
+Works with any MCP client, with a quick installer for Claude Desktop
+Storage options: local SQLite, Cloudflare for multi-device sync, or a hybrid
+Team features such as OAuth and a dashboard, per the README
03

Trade-offs

!Stored memories can contain sensitive project details, so consider where the database lives, especially with cloud sync
!The README is long and mixes release notes with documentation, so finding the basics takes scrolling
!The README includes first-time setup expectations and migration notices, which suggests some rough edges on upgrade
!Automatic capture means stale or wrong notes can be recalled; review what is stored
05

Maintenance check

ActiveChecked: 2026-10-25
Last commit
2026-10-25
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v12.3.1 (2026-10-23)
Open issues
28
Recent issues with at least one comment
9/12
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 10, 17, 72, 17, 50, 43, 33, 83, 59, 46, 59, 4

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #1146 logging: 573 unsanitised f-string logger calls remain outside the three files #1119 cleared51 comments · 2026-09-06
  • #1359 Maintainer triage digest28 comments · 2026-09-28
  • #1346 RFC: harvest design-extraction — capturing long-form reasoning and tool-results the pipeline drops6 comments · 2026-09-27
  • #1181 [First-time contributor] Looking for beginner-friendly issues to contribute6 comments · 2026-09-08
  • #1526 hooks: inbox for inter-agent messages (sentinel tags since the last check)5 comments · 2026-10-14

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You use Claude Code, Claude Desktop, Cursor, VS Code or another MCP client and want chat sessions to stop starting from zero.
  • You want a choice of storage: local SQLite, Cloudflare for multi-device sync, or a hybrid.
  • You need team features: the README lists OAuth, a dashboard and document ingestion.
Look elsewhere if
  • Your problem is codebase navigation rather than conversation memory; a code-graph tool or a project scaffold fits better.
  • You handle sensitive material and cannot put it in a persistent store, especially with cloud sync.
  • You want a short README to start from: it mixes release notes with documentation.
06

How it differs

letta logovs letta★ 25.3k

Letta replaces your assistant with its own long-lived agent. MCP Memory Service keeps your assistant and adds memory behind MCP.

Full comparison →
mex logovs mex★ 1.8k

mex stores memory as plain markdown files in your repo, so it is reviewable and diffable. MCP Memory Service stores it in a database that survives across projects and sessions.

Full comparison →
07

Compatibility

MCP Ecosystem
Native
Verified via docs
Claude
Supported
Verified via docs
Cursor
Supported
Verified via docs
VS Code
Supported
Verified via docs
JetBrains IDEs
Supported
Verified via docs
08

Quick start

1
$ pip install mcp-memory-service
09

Use cases

↳Maintaining AI context across multiple development sessions.
↳Avoiding repetitive explanations of project architecture and tech stack to AI.
↳Enhancing continuous and intelligent collaboration with AI assistants.
10

Alternatives

⚡Top VS:
VSmex★1.8k→VSletta★25.3k→VSmemorix★873→VSagentic-cursorrules★644→
mex logo
mex★ 1.8k
Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
VSCompare→
letta logo
letta★ 25.3k
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
VSCompare→
memorix logo
memorix★ 873
Cross-Agent Memory Bridge Persistent memory for AI coding agents across Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro via MCP. Never re-explain your project again.
VSCompare→
agentic-cursorrules logo
agentic-cursorrules★ 644
A practical approach to managing multiple AI agents in Cursor through strict file-tree partitioning and domain boundaries.
VSCompare→
GitHub MCP Server logo
GitHub MCP Server★ 34.0k
GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).
VSCompare→
fastapi_mcp logo
fastapi_mcp★ 12.0k
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
VSCompare→
pal-mcp-server logo
pal-mcp-server★ 11.8k
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
VSCompare→
ida-pro-mcp logo
ida-pro-mcp★ 13.2k
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
VSCompare→
See all alternatives →

Featured in these lists

  • Best Memory Tools for AI Agents and Coding Assistants

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
doobidoo /
mcp-memory-service
↗

Persistent memory across AI sessions for MCP clients

2.1k365Apache-2.0
Last commit1d ago
StatusActive
CategoryMemory & Context
Contributors136
Latest releasev12.3.1
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.