mcp-sequentialthinking-tools for Claude Code: Setup & Config

What you can do with mcp-sequentialthinking-tools in Claude Code

Pick it for inspectable session-based planning with honest, limited tool-name validation.

• Record explicit planning steps for a complex agent task
• Inspect or clear history during a long agent workflow

Before you start: mcp-sequentialthinking-tools in Claude Code

• npx
• An MCP-compatible client

The history limit is per session and defaults to 1000. Its stdio transport accepts Content-Length framing and newline-delimited JSON used by older tmcp tooling.

mcp-sequentialthinking-tools Claude Code configuration

1. Choose Claude Code configuration scope

   For mcp-sequentialthinking-tools, open Project scope: .mcp.json at the repository root. Project JSON: merge into mcpServers; user scope: use the CLI.

2. Add mcp-sequentialthinking-tools to Claude Code

   Use the mcp-sequentialthinking-tools entry below in mcpServers. Keep mcp-sequentialthinking-tools's documented stdio connection fields and your other Claude Code entries.

3. Check mcp-sequentialthinking-tools in Claude Code

   mcp-sequentialthinking-tools: Inspect claude mcp list and /mcp status.

{
  "mcpServers": {
    "mcp-sequentialthinking-tools": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-sequentialthinking-tools"
      ],
      "env": {
        "MAX_HISTORY_SIZE": "<maximum recorded steps per session; default 1000>"
      }
    }
  }
}

claude mcp add-json --scope project 'mcp-sequentialthinking-tools' '{"type":"stdio","command":"npx","args":["-y","mcp-sequentialthinking-tools"],"env":{"MAX_HISTORY_SIZE":"<maximum recorded steps per session; default 1000>"}}'

mcp-sequentialthinking-tools tools available to Claude Code

mcp-sequentialthinking-tools's stored tool list documents 3 tools; compare it with Claude Code's connected tool list, because the stored list is not a live check.

sequentialthinking_tools

For mcp-sequentialthinking-tools's sequentialthinking_tools, review the permission request and arguments in Claude Code before approval.

Record one reasoning step and optionally validate model-proposed tools against a supplied list.

get_thinking_history

For mcp-sequentialthinking-tools's get_thinking_history, review the permission request and arguments in Claude Code before approval.

clear_thinking_history

For mcp-sequentialthinking-tools's clear_thinking_history, review the permission request and arguments in Claude Code before approval.

Delete one session history or clear all session histories.

mcp-sequentialthinking-tools: full stored tool descriptions

Troubleshooting mcp-sequentialthinking-tools in Claude Code

• If mcp-sequentialthinking-tools fails to start, check npx mcp-sequentialthinking-tools (Node.js/npm), the working directory, and Claude Code's selected scope; inspect claude mcp list and /mcp.
• mcp-sequentialthinking-tools: check MAX_HISTORY_SIZE; keep credentials out of shared .mcp.json.
• mcp-sequentialthinking-tools uses stdio here: Claude Code must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
• Known limitation: Does not discover available tools or select tools for the model
• Known limitation: Adds unnecessary overhead for trivial requests
• Known limitation: Text filtering is not a guarantee against adversarial input
• General Claude Code troubleshooting lives in the /clients/claude-code guide.

Frequently asked questions