Memory Mcp
by chenxiaofiecommunityv0.2.1
10
2
A persistent memory MCP service for Claude Code that automatically saves conversations and retrieves relevant history across sessions.
From the registry: 情景+实体记忆 MCP 服务，为 Claude Code 提供持久化记忆能力
Install & configure
Prerequisites
- requiredInstall uvInstall Python uv package runner
https://docs.astral.sh/uv/$ curl -LsSf https://astral.sh/uv/install.sh | sh - requiredPython 3.10-3.13Python runtime (chromadb not compatible with Python 3.14+)
- requiredInitialize vector modelDownload vector model (~400MB, one-time)
$ uvx --from chenxiaofie-memory-mcp memory-mcp-init
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `memory-mcp-chenxiaofie` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install uv** — Install Python uv package runner Run: `curl -LsSf https://astral.sh/uv/install.sh | sh` (https://docs.astral.sh/uv/)
- **Python 3.10-3.13** — Python runtime (chromadb not compatible with Python 3.14+)
- **Initialize vector model** — Download vector model (~400MB, one-time) Run: `uvx --from chenxiaofie-memory-mcp memory-mcp-init`
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","chenxiaofie-memory-mcp","memory-mcp"]
Note: Hooks recommended for full automatic message saving.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: Hooks recommended for full automatic message saving.
Tools (17)
memory_start_episode
Start a new episode
memory_close_episode
Close and archive current episode
memory_get_current_episode
Get current active episode
memory_add_entity
Add a knowledge entity
memory_confirm_entity
Confirm a detected entity candidate
memory_reject_candidate
Reject a false detection
memory_deprecate_entity
Mark an entity as outdated
memory_get_pending
List pending entity candidates
memory_recall
Semantic search across episodes and entities
memory_search_by_type
Search entities by type
memory_get_episode_detail
Get full episode details
memory_list_episodes
List all episodes chronologically
memory_stats
Get system statistics
memory_encoder_status
Check vector encoder status
Prerequisites
- • Python 3.10
- • Python 3.14+
Packages
chenxiaofie-memory-mcp
pypiv0.2.1transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Feb 12, 2026
- Last commit
- Feb 13, 2026
- Registry name
- io.github.chenxiaofie/memory-mcp