S
spences10/mcp-sequentialthinking-tools
Suggest which MCP tool to use at each step
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
- 复制上面的命令
- 粘成
claude_desktop_config.json里mcpServers的一项（本地服务器用 command + args，示例见 客户端接法） - 重启客户端
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"spences10-mcp-sequentialthinking-tools": {
"command": "npx",
"args": ["-y", "mcp-sequentialthinking-tools"]
}
}
}解析自我们于 2026-11-05 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"spences10-mcp-sequentialthinking-tools": {
"command": "npx",
"args": ["-y", "mcp-sequentialthinking-tools"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio spences10-mcp-sequentialthinking-tools -- npx -y mcp-sequentialthinking-tools
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
npx -y mcp-sequentialthinking-tools
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx -y mcp-sequentialthinking-tools。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
我们收录于 2026-11-05；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
# mcp-sequentialthinking-tools
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
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.
It does not discover your other MCP tools and it does not
choose tools for the model. If you pass availabletools and
recommendedtools, the server validates that the recommended names
exist and stores the step.
## Why use it?
Use this when a task benefits from explicit, inspectable reasoning:
breaking a messy problem into steps;
revising or branching a plan;
keeping a small reasoning history by session;
validating tool-plan names against a supplied tool list;
clearing or inspecting reasoning history during a long agent run.
Do not use it for trivial requests. It adds overhead.
## Tools
### sequentialthinkingtools
Records one thought.
Required parameters:
thought — current reasoning step
thoughtnumber — current step number
totalthoughts — current estimate; automatically raised if lower
than thoughtnumber
nextthoughtneeded — whether another thought is needed
Optional parameters:
sessionid — history bucket; defaults to default
isrevision, revisesthought
branchfromthought, branchid
needsmorethoughts
availabletools — array of tool names or { name, description }
objects
recommendedtools — model-authored recommendations to
validate/store
remainingsteps — short list of upcoming steps
Example:
json
"sessionid": "svelte-debug",
"thought": "First inspect the route files, then run the failing check.",
"thoughtnumber": 1,
"totalthoughts": 3,
"nextthoughtneeded": true,
"availabletools": ["read", "bash"],
"recommendedtools": [
"toolname": "read",
"confidence": 0.9,
"rationale": "Need to inspect the relevant files before editing.",
"priority": 1
If recommendedtools contains a name not present in
availabletools, the call returns isError: true and does not store
the thought.
## Security posture
The server treats thought text, tool descriptions, rationales, and
remaining-step text as untrusted input. Prompt-injection-like text is
scanned and redacted before it is stored or returned in history. Calls
with redactions include securitywarnings showing which fields
matched.
This is defensive filtering, not a guarantee that arbitrary
adversarial text is safe. Do not put secrets in thoughts or tool
descriptions.
### getthinkinghistory
Returns stored thoughts for a session.
Parameters:
sessionid — defaults to default
branchid — optional branch filter
limit — max records to return; default 50, max 500
### clearthinkinghistory
Clears one session or every session.
Parameters:
sessionid — defaults to default
allsessions — clear all history buckets
## Prompt
### sequential-thinking-guidance
A short prompt that tells the model how to use this server honestly:
is a scratchpad with history, branching, revision metadata, and
optional validation for model-authored tool plans.
It does not discover your other MCP tools and it does not
choose tools for the model. If you pass availabletools and
recommendedtools, the server validates that the recommended names
exist and stores the step.
## Why use it?
Use this when a task benefits from explicit, inspectable reasoning:
breaking a messy problem into steps;
revising or branching a plan;
keeping a small reasoning history by session;
validating tool-plan names against a supplied tool list;
clearing or inspecting reasoning history during a long agent run.
Do not use it for trivial requests. It adds overhead.
## Tools
### sequentialthinkingtools
Records one thought.
Required parameters:
thought — current reasoning step
thoughtnumber — current step number
totalthoughts — current estimate; automatically raised if lower
than thoughtnumber
nextthoughtneeded — whether another thought is needed
Optional parameters:
sessionid — history bucket; defaults to default
isrevision, revisesthought
branchfromthought, branchid
needsmorethoughts
availabletools — array of tool names or { name, description }
objects
recommendedtools — model-authored recommendations to
validate/store
remainingsteps — short list of upcoming steps
Example:
json
"sessionid": "svelte-debug",
"thought": "First inspect the route files, then run the failing check.",
"thoughtnumber": 1,
"totalthoughts": 3,
"nextthoughtneeded": true,
"availabletools": ["read", "bash"],
"recommendedtools": [
"toolname": "read",
"confidence": 0.9,
"rationale": "Need to inspect the relevant files before editing.",
"priority": 1
If recommendedtools contains a name not present in
availabletools, the call returns isError: true and does not store
the thought.
## Security posture
The server treats thought text, tool descriptions, rationales, and
remaining-step text as untrusted input. Prompt-injection-like text is
scanned and redacted before it is stored or returned in history. Calls
with redactions include securitywarnings showing which fields
matched.
This is defensive filtering, not a guarantee that arbitrary
adversarial text is safe. Do not put secrets in thoughts or tool
descriptions.
### getthinkinghistory
Returns stored thoughts for a session.
Parameters:
sessionid — defaults to default
branchid — optional branch filter
limit — max records to return; default 50, max 500
### clearthinkinghistory
Clears one session or every session.
Parameters:
sessionid — defaults to default
allsessions — clear all history buckets
## Prompt
### sequential-thinking-guidance
A short prompt that tells the model how to use this server honestly:
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/spences10-mcp-sequentialthinking-tools/)
- 来源
- awesome · https://github.com/spences10/mcp-sequentialthinking-tools
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。