MCP server
Sequential Thinking MCP Server
- Maintainer
- Reference
- Runs
- Local (stdio)
- GitHub
- ★ 91,543 (whole repo, which holds more servers), last push 2026-10-24 (checked 2026-10-24)
Install the Sequential Thinking MCP Server
Pick your client. Each tab starts the same local command. Config shapes checked against each client's docs on 2026-10-25.
Run in a terminal. Everything after -- is the command that starts the server. docs
claude mcp add --transport stdio sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking
Claude Desktop only: Settings > Developer > Edit Config opens claude_desktop_config.json. Add this, save and restart the app. docs
{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project), or use the install button. docs
{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}Add to .vscode/mcp.json (note the "servers" key and the type), or use the install button. Command Palette > "MCP: Open User Configuration" for all workspaces. docs
{
"servers": {
"sequential-thinking": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}Run codex mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking, or add this to ~/.codex/config.toml. docs
[mcp_servers.sequential-thinking] command = "npx" args = ["-y", "@modelcontextprotocol/server-sequential-thinking"]
Run in a terminal (-s user adds it for all projects; the default is this project). docs
gemini mcp add -s user sequential-thinking npx -- -y @modelcontextprotocol/server-sequential-thinking
Run in a terminal; it writes ~/.copilot/mcp-config.json. docs
copilot mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking
Add to mcp_config.json: ~/.config/devin/mcp_config.json on macOS and Linux (older installs: ~/.codeium/windsurf/mcp_config.json), %APPDATA%\devin\ on Windows. docs
{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}Add to Zed's settings.json (or Settings > AI > MCP Servers > Add Server). Remote servers without an Authorization header sign in with OAuth. docs
{
"context_servers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}Add to opencode.json in the project (or ~/.config/opencode/opencode.json). docs
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"sequential-thinking": {
"type": "local",
"command": [
"npx",
"-y",
"@modelcontextprotocol/server-sequential-thinking"
],
"enabled": true
}
}
}Add to ~/.kiro/settings/mcp.json (all projects) or .kiro/settings/mcp.json (this project). docs
{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}MCP Servers > Configure > Configure MCP Servers opens cline_mcp_settings.json; add this entry. docs
{
"mcpServers": {
"sequential-thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}Security notes
- The local server runs with your user's permissions (npx downloads it from npm on first run).
Alternatives
- MiniMaxofficial · ★ 1.6k
Text to speech, voice cloning, image and video generation with MiniMax models.
- Hugging Faceofficial · ★ 308
Search models, datasets, papers and Spaces, and run Gradio apps on the Hub.
- Weights & Biasesofficial · ★ 72
Query W&B experiment runs and Weave traces, and write reports.
- ElevenLabsofficial
Text to speech, voice cloning, transcription and sound effects.
- Graphitiofficial
Temporal knowledge-graph memory that tracks how facts change over time.
- Mem0 / OpenMemoryofficial
Add, search and manage long-term memories with Mem0.
- Memoryreference
A local knowledge graph the model can store facts in and recall later.
- Replicateofficial
Search and run Replicate models, and manage predictions and deployments.
FAQ
What does the Sequential Thinking MCP Server do?+
A tool for step-by-step reasoning that can revise and branch earlier steps.
Is the Sequential Thinking MCP server official?+
A reference server kept by the Model Context Protocol project in modelcontextprotocol/servers: an example to learn from, not hardened for production.
How do I add Sequential Thinking to Claude Code?+
Run: claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking. Add --scope project to share it with your team through .mcp.json.
How do I use the Sequential Thinking MCP server in Cursor or VS Code?+
Open the Cursor or VS Code tab above: it has the mcp.json entry and a one-click install link. Cursor uses the "mcpServers" key; VS Code uses "servers" and needs a type ("stdio").
Does Sequential Thinking work in ChatGPT and claude.ai?+
No: it runs locally over stdio, and ChatGPT and claude.ai only connect to remote servers. Use it in Claude Desktop, Claude Code, Cursor, VS Code or another client that can start a local process.
What are the alternatives to the Sequential Thinking MCP server?+
Other ai & memory MCP servers: MiniMax, Hugging Face, Weights & Biases, ElevenLabs and Graphiti.