A token-saving MCP server for Windows. Feeds AI agents structured UI Automation state instead of screenshots — ~94-98% fewer perception tokens per action, measured.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add ai-process-manager-aipm -- npx -y aipm-mcp-server~/.codex/config.toml
[mcp_servers.ai-process-manager-aipm]
command = "npx"
args = ["-y", "aipm-mcp-server"]
# codex mcp add ai-process-manager-aipm -- npx -y aipm-mcp-server~/.cursor/mcp.json
{
"mcpServers": {
"ai-process-manager-aipm": {
"command": "npx",
"args": [
"-y",
"aipm-mcp-server"
]
}
}
}.vscode/mcp.json
{
"servers": {
"ai-process-manager-aipm": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"aipm-mcp-server"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"ai-process-manager-aipm": {
"command": "npx",
"args": [
"-y",
"aipm-mcp-server"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"ai-process-manager-aipm": {
"command": "npx",
"args": [
"-y",
"aipm-mcp-server"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"ai-process-manager-aipm": {
"command": "npx",
"args": [
"-y",
"aipm-mcp-server"
]
}
}
}