Qwen Memory MCP
The Qwen Memory MCP server provides long-term, cross-session memory management for AI agents, powered by Qwen, and exposed via the Model Context Protocol (MCP).
Write Memories (
memory_write): Persist durable information about a user (preferences, facts, commitments, or events). Qwen automatically derives a summary, tags, importance score, and memory kind. You can optionally override the salience score or attach a source session ID.Search Memories (
memory_search): Perform semantic search over stored memories, ranked by similarity, importance, recency, and recall frequency. Returns up to 50 matches (default 5) and reinforces recalled memories.Recall Context Within a Token Budget (
memory_recall_context): Retrieve the most critical memories relevant to a query, packed to fit within a specified token budget (up to 32,000 tokens) — ideal for injecting long-term memory into a limited context window.Consolidate and Forget (
memory_forget): Run a maintenance pass that merges related memories, flags contradicted or outdated items, and decays stale low-importance memories. Returns a report of what was consolidated, archived, forgotten, and retained.
Key properties:
All memories are namespaced by
userId, enabling one server to serve many users/agents simultaneously.Works offline without an API key (falls back to local deterministic intelligence).
Supports both
stdioand Streamable HTTP transports for local and cloud deployment.
Integrates with Alibaba Cloud's Qwen (via DashScope) for embeddings and intelligence, and uses Alibaba Cloud RDS/PolarDB for MySQL as a production storage backend for persistent memory.
Allows using MySQL (specifically Alibaba Cloud RDS/PolarDB) as a persistent storage backend for memory data, enabling durable storage of memories.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Qwen Memory MCP Remember that I prefer dark mode in all apps."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Qwen Memory MCP
Long-term memory for AI agents, powered by Qwen on Alibaba Cloud and exposed over the Model Context Protocol (MCP). Any MCP-capable agent gains durable, cross-session memory that accumulates experience, retrieves what matters within a limited context window, and forgets what is outdated.
Hackathon track: Track 1 - MemoryAgent. License: MIT. Copyright (c) 2026 JHELY GLOBAL SL.
Repository: https://github.com/John-CEO-HQ/qwen-memory-mcp
Demo video: https://youtu.be/ZxXKvVY6iMQ
This project is a learning experiment for the Qwen Cloud Hackathon: a standalone MCP server for agent memory on Alibaba Cloud.
Documentation
Guide | Purpose |
Master index: testing phases and pass criteria | |
Accounts, API keys, regions, cost guardrails | |
Live Qwen / DashScope tests from your machine | |
Alibaba deploy + verify deployed URL | |
Full install, local run, Alibaba production deploy, troubleshooting | |
Instructions for hackathon judges | |
Alibaba ECS / Function Compute quick reference | |
Agent conventions and isolation contract |
Related MCP server: mindcore-memory-mcp
Why
Agents feel sharp inside a single conversation and amnesiac across sessions. This server gives an agent a managed memory layer that does four things well:
Write - extract a durable memory (preference, fact, commitment, event), with a Qwen-derived summary, tags, importance (salience), and kind.
Search - semantic retrieval ranked by similarity + salience + recency + reinforcement.
Recall context - pack the most critical memories into a fixed token budget, ready to inject into a small context window.
Forget - a maintenance pass that consolidates related memories with Qwen and lets stale, low-value memories decay away.
Architecture
flowchart LR
agent["Any MCP client / agent"] -->|"MCP: write / search / recall / forget"| server["Qwen Memory MCP server (stdio or HTTP)"]
server --> service["MemoryService"]
service -->|"embeddings + reasoning"| qwen["Qwen on Alibaba Cloud Model Studio (DashScope)"]
service -->|"persist + retrieve"| store["MemoryStore"]
store --> file["File / in-memory (local + demo)"]
store --> mysql["Alibaba Cloud RDS / PolarDB for MySQL (production)"]Memory lifecycle:
flowchart TD
w["memory_write"] --> analyze["Qwen analyze: summary, tags, salience, kind"]
analyze --> embed1["Qwen embed (text-embedding-v3)"]
embed1 --> active["active memory"]
active --> s["memory_search / memory_recall_context"]
s --> rank["rank: similarity + salience + recency + reinforcement"]
rank --> pack["pack into token budget"]
s -.reinforce.-> active
active --> f["memory_forget"]
f --> cluster["cluster by embedding similarity"]
cluster --> consolidate["Qwen consolidate cluster -> canonical memory"]
consolidate --> outdated["flag contradicted items -> forgotten"]
active --> decay["decay score below threshold -> forgotten"]Quick start
npm install
# Offline demo (no API key needed - deterministic local intelligence):
npm run demo
# Run the test suite:
npm test
# Run as an MCP server over stdio (for MCP Inspector / desktop clients):
npm run build && npm startTo use the real Qwen models, copy .env.example to .env and set
QWEN_API_KEY (and optionally QWEN_BASE_URL for your region). Without a key,
the server automatically falls back to the offline deterministic intelligence
so it always runs.
MCP tools
Tool | Purpose | Key inputs |
| Persist a durable memory |
|
| Top-k semantic recall |
|
| Critical memories packed to a token budget |
|
| Consolidate + decay maintenance |
|
All memories are namespaced by userId, so one server can serve many agents.
Transports
stdio (
MCP_TRANSPORT=stdio, default) - launched as a child process by a local MCP client.Streamable HTTP (
MCP_TRANSPORT=http) - stateless JSON-RPC atPOST /mcpwith optionalAuthorization: Bearer <MCP_AUTH_TOKEN>, plusGET /health. This is the shape used for cloud deployment and remote per-user MCP URLs.
Storage
MEMORY_STORE=memory- in-process, ephemeral (tests/demo).MEMORY_STORE=file- single JSON file atMEMORY_FILE_PATH(local default).MEMORY_STORE=mysql- Alibaba Cloud RDS / PolarDB for MySQL (production); schema is created automatically. Vectors are stored as JSON and scored in the app; seesrc/memory/mysql-store.tsfor the AnalyticDB-PG (pgvector) upgrade path.
Alibaba Cloud / Qwen
The only integration points with Alibaba Cloud are
src/qwen.ts (DashScope embeddings + chat) and
src/memory/mysql-store.ts (RDS/PolarDB). See
docs/INSTALL.md for full production setup and
deploy/README.md for a short Alibaba quick reference.
Configuration
See .env.example for all variables (Qwen models, store
selection, transport, auth token, and forgetting/decay tuning).
Layout
qwen-memory-mcp/
src/
qwen.ts # Alibaba Cloud / Qwen (DashScope) intelligence [PROOF]
fake-intelligence.ts # offline deterministic intelligence (tests/demo)
intelligence.ts # picks Qwen vs fake
config.ts # env-driven config
types.ts # domain types
memory/
store.ts # MemoryStore interface
file-store.ts # file / in-memory store
mysql-store.ts # Alibaba RDS / PolarDB store [PROOF]
create-store.ts # store factory
ranking.ts # retrieval ranking + token-budget packing
forgetting.ts # clustering + consolidation + decay
service.ts # MemoryService (orchestration)
server.ts # MCP server + 4 tools
transports/
stdio.ts # stdio transport
http.ts # streamable HTTP transport (stateless)
index.ts # entry point
demo/cli.ts # multi-session offline demo
test/ # vitest suite
deploy/ # Alibaba Cloud deployment docs
DockerfileLicense
MIT License. Copyright (c) 2026 JHELY GLOBAL SL. See LICENSE.
Available Tools
4 toolsmemory_forgetConsolidate and forgetA
Runs the maintenance pass: clusters of related memories are merged by Qwen into one canonical memory, contradicted/outdated items are forgotten, and stale low-importance memories decay away. Returns a report of what was consolidated, archived, forgotten, and retained.
Inputs: userId (required).
memory_recall_contextRecall context within a token budgetB
Returns the most critical memories for a query, greedily packed to fit a token budget, as a ready-to-inject context block. Use this to load long-term memory into a limited context window before answering.
Inputs: query (required), userId (required), tokenBudget (required).
memory_searchSearch memoriesA
Semantic search over a user's memories, ranked by similarity, importance, recency, and how often each memory has been recalled. Returns the top matches. Recalled memories are reinforced.
Inputs: query (required), userId (required), k.
memory_writeWrite memoryA
Persist something worth remembering about a user (a preference, fact, commitment, or event). Qwen derives a short summary, tags, importance (salience), and kind. Call this whenever the user reveals durable information you should recall in future sessions.
Inputs: userId (required), content (required), salience, sourceSession.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: writing new memories, searching them, recalling context for a query, and running maintenance. No overlap in functionality.
All tool names follow a consistent 'memory_<verb>' pattern, making the action clear and predictable.
Four tools cover the core memory operations (write, search, recall, maintenance) without unnecessary bloat. The scope is appropriate for a memory management server.
Missing explicit update and list operations; however, the automatic maintenance and selective retrieval cover common use cases. Gaps exist for direct manipulation of individual memories.
Maintenance
Related MCP Connectors
Hosted memory for AI agents over MCP. One memory shared by all your agents.
Persistent memory for AI agents to retain, retrieve, and recall conversation context through MCP.
An MCP memory server. One memory your agents share — across models, devices and apps.
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides AI agents with persistent memory capabilities through Mem0, allowing them to store, retrieve, and semantically search memories.687MIT
- AlicenseAqualityCmaintenanceA production-grade long-term memory MCP server that enables AI agents to persist and recall memories across sessions with importance weighting, confidence calibration, and efficient context window management.918 PyPI1MIT
- AlicenseNot gradedqualityDmaintenancePersistent, searchable memory for AI agents over the Model Context Protocol, enabling memory storage, full-text search with BM25 ranking, and retrieval across sessions.8 npmMIT
- FlicenseNot gradedqualityBmaintenanceA persistent memory server for AI agents using MCP protocol, enabling semantic storage and retrieval of dialogues, documents, and agent states.-