Happy slice of mcp pizzaMCP.pizza

kindex

MCP.Pizza Chef: jmcentire

Kindex helps your AI assistant remember and understand what you discuss by building a knowledge graph from your conversations and projects. It works with apps like Cursor and others that support MCP, letting your AI keep track of important ideas and context over time. Setup requires some developer steps, but once running, it improves how your AI uses past information to assist you smarter and more efficiently.

Coding
Other

Use This MCP server To

Remember details from my conversations for future reference Connect related ideas across different chats and projects Provide AI assistants with context-aware knowledge Summarize complex information into concise insights Manage how much context AI gets based on token limits Search and retrieve past conversation knowledge easily Help AI avoid starting sessions without background info

README

Kindex

Python 3.10+ MIT License v0.32.0 PyPI MCP Market Tests MCP Plugin

The memory layer AI coding agents don't have.

Kindex does one thing. It knows what you know.

It's a persistent knowledge graph for AI-assisted workflows. It indexes your conversations, projects, and intellectual work so that Claude Code, Codex, Gemini CLI, Google Antigravity, OpenCode, Cursor, and other MCP-capable agents never start a session blind. Available as a free MCP plugin or standalone CLI.

Memory plugins capture what happened. Kindex captures what it means and how it connects. Most memory tools are session archives with search. Kindex is a weighted knowledge graph that grows intelligence over time — understanding relationships, surfacing constraints, and managing exactly how much context to inject based on your available token budget.

Docs: kindex.tools is the canonical public site, served by the companion Fly static app. This repo also publishes its docs/ directory at jmcentire.github.io/kindex. Human setup lives in docs/human-guide.md; agent operating rules live in docs/mcp-agent-guide.md.

Install

Pick whichever installer you already use. They all install the same kin and kin-mcp binaries.

# pip
pip install 'kindex[mcp]'

# uv (single binary, no virtualenv)
uv tool install 'kindex[mcp]'

# uvx (no install — runs from cache, useful for one-off MCP invocation)
uvx --from 'kindex[mcp]' kin-mcp --help

# from source
git clone https://github.com/jmcentire/kindex && cd kindex && make install

Then initialize the graph:

kin init

Extras — combine in one install ('kindex[mcp,llm,reminders]') or use 'kindex[all]':

kindex FAQ

Can I use kindex to remember and connect information from my conversations?
Yes — kindex builds a knowledge graph from your chats to help AI assistants understand context better.
Can I use kindex with Cursor?
Yes — kindex works as a server that Cursor and other MCP-capable apps can connect to for enhanced memory.
Do I need an API key or account to use kindex?
No — kindex runs locally or on your server without requiring external accounts or keys.
How hard is it to set up kindex?
It requires developer-level setup, including installing via pip or uvx and initializing the knowledge graph.
Which AI assistants work with kindex?
It supports Claude Code, Codex, Gemini CLI, Google Antigravity, OpenCode, Cursor, and other MCP-enabled agents.