AI Context Kit runs on your own machine — the client starts it, so there is no endpoint to ping. 52 installs a week from npm. Last commit 16 Sep 2026.
Lint, measure, and sync AI context files across Cursor, Claude Code, Copilot.
Today is the operative word: we check AI Context Kit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ai-context-kit -- npx -y ai-context-kit
{
"mcpServers": {
"ai-context-kit": {
"args": [
"-y",
"ai-context-kit"
],
"command": "npx"
}
}
}
[mcp_servers.ai-context-kit]
command = "npx"
args = ["-y", "ai-context-kit"]
{
"mcpServers": {
"ai-context-kit": {
"args": [
"-y",
"ai-context-kit"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ai-context-kit": {
"args": [
"-y",
"ai-context-kit"
],
"command": "npx"
}
}
}
Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
Share context, detect conflicts, and message across parallel Claude Code sessions
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.
Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase
Research-backed linting + generation for agent context files (CLAUDE.md, AGENTS.md, Cursor rules).
Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot.
Wontopos (WOS) long-term memory - one memory across Claude Code, Cursor, and your agents.
Answers built from our own checks of this server.