Does MCP work in all Cursor modes?
No, MCP tools are only available in Composer and Agent modes.
@Zanedname
Basic information
测试仓库 - Windows CMD 测试服务器
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"sequential_thinking": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
}
}
}A detailed tool for dynamic and reflective problem-solving through thoughts. This tool helps analyze problems through a flexible thinking process that can adapt and evolve. Each thought can build on, question, or revise previous insights as understanding deepens. When to use this tool: - Breaking down complex problems into steps - Planning and design with room for revision - Analysis that might need course correction - Problems where the full scope might not be clear initially - Problems that require a multi-step solution - Tasks that need to maintain context over multiple steps - Situations where irrelevant information needs to be filtered out Key features: - You can adjust total_thoughts up or down as you progress - You can question or revise previous thoughts - You can add more thoughts even after reaching what seemed like the end - You can express uncertainty and explore alternative approaches - Not every thought needs to build linearly - you can branch or backtrack - Generates a solution hypothesis - Verifies the hypothesis based on the Chain of Thought steps - Repeats the process until satisfied - Provides a correct answer Parameters explained: - thought: Your current thinking step, which can include: * Regular analytical steps * Revisions of previous thoughts * Questions about previous decisions * Realizations about needing more analysis * Changes in approach * Hypothesis generation * Hypothesis verification - nextThoughtNeeded: True if you need more thinking, even if at what seemed like the end - thoughtNumber: Current number in sequence (can go beyond initial total if needed) - totalThoughts: Current estimate of thoughts needed (can be adjusted up/down) - isRevision: A boolean indicating if this thought revises previous thinking - revisesThought: If is_revision is true, which thought number is being reconsidered - branchFromThought: If branching, which thought number is the branching point - branchId: Identifier for the current branch (if any) - needsMoreThoughts: If reaching end but realizing more thoughts needed You should: 1. Start with an initial estimate of needed thoughts, but be ready to adjust 2. Feel free to question or revise previous thoughts 3. Don't hesitate to add more thoughts if needed, even at the "end" 4. Express uncertainty when present 5. Mark thoughts that revise previous thinking or branch into new paths 6. Ignore information that is irrelevant to the current step 7. Generate a solution hypothesis when appropriate 8. Verify the hypothesis based on the Chain of Thought steps 9. Repeat the process until satisfied with the solution 10. Provide a single, ideally correct answer as the final output 11. Only set nextThoughtNeeded to false when truly done and a satisfactory answer is reached
This guide provides step-by-step instructions for configuring Model Context Protocol (MCP) servers in Cursor IDE version 0.46 on Windows. MCP allows the Cursor AI assistant to interact with external tools and services, such as web search, browser automation, file system access, and GitHub management. It is intended for developers using Cursor on Windows who want to extend AI capabilities with third-party tools.
Follow one of three installation methods described in the guide: (1) add servers through Cursor’s settings UI (Features → MCP Servers → Add New MCP Server, using Stdio/local type), (2) create a project-level .cursor/mcp.json file, or (3) create a global mcp.json in %APPDATA%\Cursor. The guide lists example commands for servers such as Sequential Thinking (npx -y @modelcontextprotocol/server-sequential-thinking) and Brave Search (env BRAVE_API_KEY=[key] npx -y @modelcontextprotocol/server-brave-search). Environment variables can be set inline, via PowerShell, or through Windows system settings.
No, MCP tools are only available in Composer and Agent modes.
The server status indicator should be green, and a terminal window will appear when the server is used.
There is no hard limit, but it is recommended to add only the servers needed for the current task to reduce resource consumption.
You can add the `.cursor/mcp.json` file to version control or use configuration sync tools.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Comments