Montycat MCP — AI skill for Claude Code
Shared, persistent memory for AI agents.
How to install Montycat MCP
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open MontyGovernance/montycat-mcp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Montycat MCP does
Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Cursor, Codex, and any MCP client.
Alternatives in AI
- Nocturne Memory — A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents 1.3k ★
- Update Branch Name — by giselles-ai - Updates branch names with proper prefixes and formats, enforcing naming conventions, supporti 502 ★
- Agenvoy — Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets 474 ★
README
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.
[](https://pypi.org/project/montycat-mcp/) [](https://pypi.org/project/montycat-mcp/) [](LICENSE)
- Memory that survives the chat. Decisions, preferences, and project context carry into the next session.
- One memory, many agents. Every MCP client you use works from the same facts.
- Recall by meaning, keyword, or both. Vector search finds a memory when the wording differs, BM25 nails exact identifiers, and hybrid mode fuses the two. Exact-key and metadata lookup too.
- Yours. Server, engine, and embeddings run on your machine. No hosted memory service, no cloud embedding API.
Install
**Claude Desktop** — download the latest `.mcpb` from [Releases](https://github.com/MontyGovernance/montycat-mcp/releases/latest) and drag it into Claude Desktop. No Python needed.
**Claude Code** — install [`uv`](https://docs.astral.sh/uv/getting-started/installation/), 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-mcpThe engine
Memory lives in a [Montycat Semantic](https://montygovernance.com) engine. Montycat MCP starts a loc
Related Skills
Mnemon
Self-hosted, cross-device long-term memory for AI agents via MCP — one vault shared across any MCP client (Cla
Flyarchive
FlyArchive — self-hosted personal document archive and knowledge base with hybrid semantic + full-text search.
Claude Persistent Memory
Give Claude Code persistent memory across sessions. Hybrid BM25 + vector semantic search, auto-structuring via
Council Hub
Open-source MCP server for coordinating multiple LLM agents in shared rooms with persistent transcripts and se
Imprint Memory
Persistent memory system for Claude Code — hybrid search (FTS5 + vector), message bus, task queue. Works as MC
Memrain
Self-hosted memory for your AI agents: hybrid vector + keyword + entity-graph search over your notes and code,
Related Agents
Python RAG Backend Engineer
Production-grade Python RAG backend engineer specializing in ChromaDB vector storage, sentence-transformers em
Cx RAG Researcher
Use this agent when researching Mozilla user experience data. Queries three sources — SUMO/Kitsune forum threa
Plugin Host Parity Checker
Checks that the shared skills/ tree, the three host manifests (.claude-plugin/, .cursor-plugin/, .codex-plugin
