An MCP server implementation that enables AI to perform interleaved sequential thinking with dynamic tool calling. This server allows AI to alternate between reasoning, tool execution, and result analysis in a flexible "think-execute-reflect" cycle.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add interleaved-sequential-thinking -- npx -y @jochenyang/interleaved-thinking~/.codex/config.toml
[mcp_servers.interleaved-sequential-thinking]
command = "npx"
args = ["-y", "@jochenyang/interleaved-thinking"]
# codex mcp add interleaved-sequential-thinking -- npx -y @jochenyang/interleaved-thinking~/.cursor/mcp.json
{
"mcpServers": {
"interleaved-sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@jochenyang/interleaved-thinking"
]
}
}
}.vscode/mcp.json
{
"servers": {
"interleaved-sequential-thinking": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@jochenyang/interleaved-thinking"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"interleaved-sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@jochenyang/interleaved-thinking"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"interleaved-sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@jochenyang/interleaved-thinking"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"interleaved-sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@jochenyang/interleaved-thinking"
]
}
}
}