Montycat MCP - Shared Memory for AI Agents
A self-hosted MCP server that gives AI agents persistent, searchable memory. Claude, Codex, Cursor, and any Model Context Protocol client write to one memory and read each other's.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx memocat-mcp==0.4.3Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
MONTYCAT_URI=<secret> MONTYCAT_TLS=<value> claude mcp add io.github.montygovernance-memocat-mcp -- uvx memocat-mcp==0.4.3在終端機中執行。
{ "mcpServers": { "io.github.montygovernance-memocat-mcp": { "command": "uvx", "args": [ "memocat-mcp==0.4.3" ], "env": { "MONTYCAT_URI": "<secret>", "MONTYCAT_TLS": "<value>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
A self-hosted MCP server that gives AI agents persistent, searchable memory. Claude, Codex, Cursor, and any Model Context Protocol client write to one memory and read each other's.
One shared, persistent memory across AI agents and systems, with semantic recall and live updates.
Claude Desktop — download
montycat-mcp.mcpb
and drag it into Claude Desktop. No Python needed. That link always serves the
current release; every release
also carries a version-named copy and a .sha256 to check it against.
Claude Code — install uv, then:
/plugin marketplace add MontyGovernance/montycat-mcp
/plugin install montycat-mcp@montygovernance
/mcp confirms the montycat server is connected.
Codex, Cursor, other MCP clients — point your client's stdio config at
uvx montycat-mcp (Python 3.10+). For Codex:
codex mcp add montycat -- uvx montycat-mcp
Memory lives in a Montycat Semantic engine. Montycat MCP starts a local one for you, so most people can stop reading here.
Point it at an engine you already run:
export MONTYCAT_URI="montycat://memory-agent:password@localhost:21210/memories"
export MONTYCAT_TLS=true # remote engines only
Or start one yourself with Docker:
docker run -d --name montycat -p 21210:21210 -p 21211:21211 \
-e MONTYCAT_SUPEROWNER=admin -e MONTYCAT_PASSWORD=change-me \
-v montycat_data:/var/lib/.montycat \
montygovernance/montycat:semantic
On Apple Silicon use the arm64-semantic tag instead — semantic is the amd64
image, and it crashes under emulation. Port 21211 carries live memory watches.
Talk to your agent normally; it picks the tool.
Remember that the team chose PostgreSQL for the billing service.
What did we decide about the billing database?
Save this to the shared
engineeringscope.
scope decides where a memory lives — alice for private, engineering for a
team, shared for common. It is a namespace, not a security boundary: for real
isolation, give each MCP server its own least-privilege Montycat credential.
For persistent namespaces, cache is a capacity in MB and compression is
chosen by montycat_create_keyspace. Compression cannot be changed after the
keyspace is created; migrate into a new keyspace to use a different setting.
Cache capacity can be changed later with montycat_update_cache.
Destructive tools are declared as such, so your client's confirmation prompts apply.
All three verification settings are optional. With only MONTYCAT_TLS=true,
MCP retains the historical encrypted-but-unverified behavior; with TLS unset or
false, existing plaintext configurations are unchanged.
| MONTYCAT_DEFAULT_KEYSPACE | Memory namespace; memory by default |
| MONTYCAT_SCOPE | Default scope when a call omits one |
| MONTYCAT_AUTO_PROVISION | Create a permitted scope on first use; true by default |
| MONTYCAT_AUTOSTART | off to require an already-running engine |
Compose setup and the full variable list: compose.yaml and the plugin guide.
Changelog · Privacy · Issues · Docs · Docker Hub
Existing MemoCat installs keep working: memocat-mcp, MEMOCAT_*, and
memocat:// are still supported. New setups should use the Montycat names.
MIT
One shared, persistent memory across AI agents and systems, with semantic recall and live updates.
{ "mcpServers": { "io.github.montygovernance-memocat-mcp": { "command": "uvx", "args": [ "memocat-mcp==0.4.3" ], "env": { "MONTYCAT_URI": "<secret>", "MONTYCAT_TLS": "<value>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數:MONTYCAT_URI, MONTYCAT_TLS。
MemoCat — Shared AI Memory 透過 stdio 在本機執行。
上次檢查時間:2026-11-09。 One shared, persistent memory across AI agents and systems, with semantic recall and live updates.