Lightweight MCP sequential thinking scratchpad with optional tool-plan validation
Mcp sequentialthinking tools mcp server connects MCP Sequentialthinking Tools to AI assistants that speak the Model Context Protocol. Lightweight MCP sequential thinking scratchpad with optional tool-plan validation.
A lightweight MCP server for recording sequential reasoning steps. It is a scratchpad with history, branching, revision metadata, and optional validation for model-authored tool plans.
Once connected, the assistant can call these 11 tools directly:
thought — current reasoning stepthought_number — current step numbertotal_thoughts — current estimate; automatically raised if lowernext_thought_needed — whether another thought is neededsession_id — history bucket; defaults to defaultneeds_more_thoughts — available_tools — array of tool names or { name, description }recommended_tools — model-authored recommendations toremaining_steps — short list of upcoming stepssequentialthinking_tools — If recommended_tools contains a name not present in available_tools, the call returns isError: true and does not store the thoughtget_thinking_history — The get_thinking_history tool exposed by this serverclear_thinking_history — The clear_thinking_history tool exposed by this serverThe server is distributed via npm as pnpm, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
The server reads one environment variable: MAX_HISTORY_SIZE. Keep credentials in your client's env block or a secrets manager rather than committing them.
Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. MCP Sequentialthinking Tools sits in that group, and the shape of its toolset — thought, thought_number, total_thoughts among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| thought | current reasoning step |
| thought_number | current step number |
| total_thoughts | current estimate; automatically raised if lower |
| next_thought_needed | whether another thought is needed |
| session_id | history bucket; defaults to default |
| needs_more_thoughts | available_tools — array of tool names or { name, description } |
| recommended_tools | model-authored recommendations to |
| remaining_steps | short list of upcoming steps |
| sequentialthinking_tools | If recommended_tools contains a name not present in available_tools, the call returns isError: true and does not store the thought. |
| get_thinking_history | The get_thinking_history tool exposed by this server. |
| clear_thinking_history | The clear_thinking_history tool exposed by this server. |
{
"mcpServers": {
"mcp-sequentialthinking-tools": {
"command": "npx",
"args": ["-y", "mcp-sequentialthinking-tools"],
"env": {
"MAX_HISTORY_SIZE": "1000"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| MAX_HISTORY_SIZE | Configuration value read at startup. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.