process_thoughtLABSCO SUMMARY
A thinking session you can leave and come back to.
The official sequential-thinking server holds the chain in memory for the length of one process. This one writes it down — so a session survives a restart, can be exported and handed to someone else, and can be analyzed for which stages you actually spent your thinking in.
What it is
A server for working through a problem in numbered steps, where each thought is categorized into a stage, stored with its metadata, and analyzed for its relationship to the others. Sessions persist on disk rather than living only in the conversation.
What you get
process_thought— records a thought with its number, the expected total, whether more are needed, and a stage from Problem Definition, Research, Analysis, Synthesis or Conclusion. Optional tags, axioms used and assumptions challenged travel with it- Revisions and branches on the same tool: mark a thought as revising an earlier one, or fork an alternative line of reasoning from a chosen thought under a named branch
generate_summary— the whole process at a glance: total thoughts, the count per stage, a timeline marking revisions and branches, and per-branch statisticsclear_historyto reset, andexport_session/import_sessionto write a session to JSON and read it back, including sessions exported by earlier versions- Persistence as an append-only JSONL log where each call appends a single fsynced line, so the file doubles as an audit trail and a truncated final line from an interrupted write is recovered automatically
Requirements
Python 3.10 or higher and the uv package manager. The shortest path is uvx mcp-sequential-thinking with no install step, or pip install mcp-sequential-thinking for a permanent one. Configuration examples are given for Claude Desktop, Cursor, VS Code, Zed, Claude Code, Windsurf and Gemini CLI, all running the published package through uvx. Sessions live at ~/.mcp_sequential_thinking/current_session.jsonl, and MCP_STORAGE_DIR moves that directory; exports are confined to an exports/ subdirectory beneath it.
Setup effort
One command — uvx mcp-sequential-thinking
USE CASES
01
Working through a decision methodically
Each thought is filed under a stage, so the record shows whether you actually did the research or jumped from problem definition to conclusion.
02
Changing your mind halfway
Mark a thought as revising an earlier one; the summary's timeline shows the revision rather than quietly overwriting what you thought before.
03
Exploring an alternative without losing the first path
Fork from a chosen thought under a branch id; branch statistics come back in the summary alongside the main line.
04
Picking up where you left off
The append-only log survives a restart, and a truncated final line from an interrupted write recovers automatically.
05
Handing the reasoning to someone else
Export the session to JSON, share the file, and let them import it — including sessions written by an earlier version.
5 tools
Listed in project docs. Your client may show a different list.
generate_summaryclear_historyexport_sessionimport_sessionBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
- uvx on PATH
- Python 3.10 or later
Where it runs
All 7 documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx mcp-sequential-thinkingMCP Clients
Claude Code, Cursor, Windsurf, Claude Desktop
JSON
{
"mcpServers": {
"sequential-thinking": {
"command": "uvx",
"args": [
"mcp-sequential-thinking"
]
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"sequential-thinking": {
"command": "uvx",
"args": [
"mcp-sequential-thinking"
]
}
}
}Zed
ZED · JSON
{
"context_servers": {
"sequential-thinking": {
"command": {
"path": "uvx",
"args": [
"mcp-sequential-thinking"
]
}
}
}
}Gemini CLI
GEMINI CLI · JSON
{
"mcpServers": {
"sequential-thinking": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-sequential-thinking"
],
"env": {}
}
}
}
