How does this server differ from tools that auto‑select tools?
It does not discover or choose tools for the model. It only records thoughts and validates that recommended tool names exist in the supplied `available_tools` list.
@spences10
基本情報
🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at each stage.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-sequentialthinking-tools": {
"command": "npx",
"args": [
"-y",
"mcp-sequentialthinking-tools"
],
"env": {
"MAX_HISTORY_SIZE": "1000"
}
}
}
}Record one step of sequential reasoning. Optionally include available_tools and recommended_tools; recommendations are validated, not generated, by this server.
Return recorded thoughts for a session. Use this to inspect or resume prior reasoning.
Clear recorded sequential-thinking history for one session or all sessions.
A lightweight MCP server for recording sequential reasoning steps. It functions as a scratchpad with history, branching, revision metadata, and optional validation for model-authored tool plans. It does not discover other MCP tools or choose tools for the model.
Install and configure via npx -y mcp-sequentialthinking-tools in your MCP client settings (e.g., Claude Desktop). Optionally set the MAX_HISTORY_SIZE environment variable (default 1000 per session). Use the provided sequentialthinking_tools, get_thinking_history, and clear_thinking_history tools, and optionally include the sequential-thinking-guidance prompt.
"default".It does not discover or choose tools for the model. It only records thoughts and validates that recommended tool names exist in the supplied `available_tools` list.
The server runs on Node.js and is invoked via `npx`. It uses the `tmcp` library for MCP transport.
History is kept in memory per session. The maximum number of entries per session is configurable via the `MAX_HISTORY_SIZE` environment variable (default 1000).
Thought text, tool descriptions, rationales, and remaining‑step text are scanned for prompt‑injection‑like content. Matching fields are redacted before storage or retrieval, and calls with redactions include `security_warnings`.
It uses a stdio transport that accepts both standard `Content‑Length` framed MCP messages and newline‑delimited JSON used by older `tmcp` tooling.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
コメント