[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73771":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":18,"rankGlobal":9,"rankLanguage":9,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":15,"starSnapshotCount":15,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},73771,"n8n-nodes-mcp","nerding-io\u002Fn8n-nodes-mcp","nerding-io","n8n custom node for MCP",null,"TypeScript",3013,523,32,56,0,3,4,30.16,"MIT License",false,"main",true,[],"2026-06-12 02:03:17","[![Verified on MseeP](https:\u002F\u002Fmseep.ai\u002Fbadge.svg)](https:\u002F\u002Fmseep.ai\u002Fapp\u002Fbd76f121-1c8f-4f5d-9c65-1eac5d81b6af)\n\n# n8n-nodes-mcp-client\n\n> **Important Note:**\n> The Server-Sent Events (SSE) transport is deprecated and replaced by the new HTTP Streamable transport. SSE remains available for legacy compatibility, but HTTP Streamable is now the recommended method for all new implementations.\n\nThis is an n8n community node that lets you interact with Model Context Protocol (MCP) servers in your n8n workflows.\n\nMCP is a protocol that enables AI models to interact with external tools and data sources in a standardized way. This node allows you to connect to MCP servers, access resources, execute tools, and use prompts.\n\n[n8n](https:\u002F\u002Fn8n.io\u002F) is a [fair-code licensed](https:\u002F\u002Fdocs.n8n.io\u002Freference\u002Flicense\u002F) workflow automation platform.\n\n[Installation](#installation)\n[Credentials](#credentials)\n[Environment Variables](#environment-variables)\n[Operations](#operations)\n[Using as a Tool](#using-as-a-tool)\n[Compatibility](#compatibility)\n[Resources](#resources)\n\n## Getting Started\n\nOfficial Quickstart Video:\n\n[![MCP Client Node Quickstart](\u002Fassets\u002Fmcp-n8n.png)](https:\u002F\u002Fyoutu.be\u002F1t8DQL-jUJk)\n\n\n\n### Community Videos\n\nShoutout to all the creators of the following n8n community videos that are great resources for learning how to use this node:\n\n- [Is MCP the Future of N8N AI Agents? (Fully Tested!)](https:\u002F\u002Fyoutu.be\u002Fsb5hCcFYPIE)\n- [Connect N8N AI Agents to EVERYTHING using MCP?](https:\u002F\u002Fyoutu.be\u002FtTDRgkD-120)\n- [Build an AI Agent That Can Use Any Tool (MCP in n8n Tutorial)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=SVZe2rdhYmA)\n- [The NEW N8N MCP is an Absolute Game-Changer (Brave Search MCP)](https:\u002F\u002Fyoutu.be\u002FRxXS_FpJyGM)\n- [MCP & n8n Automation: The Ultimate Guide for MCP AI Agents (2025)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=mbQsnrxHPwE)\n- [REVOLUÇÃO na criação de AGENTES no N8N com o MCP Server!!!](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zgH85dJcs5c) (Portuguese)\n\nIf you have a great video that you'd like to share, please let me know and I'll add it to the list!\n\n#### Interested a deeper dive into MCP?\n\nCheck out my YouTube Series [MCP Explained](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLjOCx_PNfJ4S_oOSqrMi6t9_x1GllvQZO) for more information about the Model Context Protocol.\n\n### Security Assessment\n[![MseeP.ai Security Assessment Badge](https:\u002F\u002Fmseep.net\u002Fpr\u002Fnerding-io-n8n-nodes-mcp-badge.png)](https:\u002F\u002Fmseep.ai\u002Fapp\u002Fnerding-io-n8n-nodes-mcp)\n\n\n## Installation\n\nFollow the [installation guide](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fcommunity-nodes\u002Finstallation\u002F) in the n8n community nodes documentation.\n\nAlso pay attention to Environment Variables for [using tools in AI Agents](#using-as-a-tool). It's mandatory to set the `N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE` environment variable to `true` if you want to use the MCP Client node as a tool in AI Agents.\n\n## Credentials\n\nThe MCP Client node supports three types of credentials to connect to an MCP server:\n\n### Command-line Based Transport (STDIO)\n\n![MCP Client STDIO Credentials](.\u002Fassets\u002Fcredentials.png)\n\n- **Command**: The command to start the MCP server\n- **Arguments**: Optional arguments to pass to the server command\n- **Environment Variables**: Variables to pass to the server in NAME=VALUE format\n\n### HTTP Streamable Transport (Recommended)\n\n- **HTTP Streamable URL**: The HTTP endpoint that supports streaming responses (e.g., http:\u002F\u002Flocalhost:3001\u002Fstream)\n- **Additional Headers**: Optional headers to send with requests (format: name:value, one per line)\n\nHTTP Streamable is the recommended and modern method for all new integrations, providing better efficiency and flexibility compared to SSE.\n\n#### Example: Using a Local MCP Server with HTTP Streamable\n\nThis example shows how to connect to a locally running MCP server using HTTP Streamable:\n\n1. Start a local MCP server that supports HTTP Streamable:\n   ```bash\n   npx @modelcontextprotocol\u002Fserver-example-streamable\n   ```\n\n2. Configure MCP Client credentials:\n   - In the node settings, select **Connection Type**: `HTTP Streamable`\n   - Create new credentials of type **MCP Client (HTTP Streamable) API**\n   - Set **HTTP Streamable URL**: `http:\u002F\u002Flocalhost:3001\u002Fstream`\n   - Add any required headers for authentication\n\n3. Create a workflow using the MCP Client node:\n   - Add an MCP Client node\n   - Set the Connection Type to `HTTP Streamable`\n   - Select your HTTP Streamable credentials\n   - Execute the workflow to see the results\n\n### Server-Sent Events (SSE) Transport (Deprecated, still available for legacy use)\n\n- **SSE URL**: The URL of the SSE endpoint (default: http:\u002F\u002Flocalhost:3001\u002Fsse)\n- **Messages Post Endpoint**: Optional custom endpoint for posting messages if different from the SSE URL\n- **Additional Headers**: Optional headers to send with requests (format: name:value, one per line)\n\n> **Deprecated:** SSE is deprecated and will not receive further updates, but remains available for legacy compatibility. For new projects, use HTTP Streamable.\n\n#### Example: Using a Local MCP Server with SSE (legacy)\n\nThis example shows how to connect to a locally running MCP server using Server-Sent Events (SSE):\n\n1. Start a local MCP server that supports SSE:\n   ```bash\n   npx @modelcontextprotocol\u002Fserver-example-sse\n   ```\n\n2. Configure MCP Client credentials:\n   - In the node settings, select **Connection Type**: `Server-Sent Events (SSE)`\n   - Create new credentials of type **MCP Client (SSE) API**\n   - Set **SSE URL**: `http:\u002F\u002Flocalhost:3001\u002Fsse`\n   - Add any required headers for authentication\n\n3. Create a workflow using the MCP Client node:\n   - Add an MCP Client node\n   - Set the Connection Type to `Server-Sent Events (SSE)`\n   - Select your SSE credentials\n   - Execute the workflow to see the results\n\n> **Note:** For new projects, HTTP Streamable is strongly recommended.\n\n## Environment Variables\n\nThe MCP Client node supports passing environment variables to MCP servers using the command-line based transport in two ways:\n\n### 1. Using the Credentials UI\n\nYou can add environment variables directly in the credentials configuration:\n\n![Environment Variables in Credentials](.\u002Fassets\u002Fcredentials-envs.png)\n\nThis method is useful for individual setups and testing. The values are stored securely as credentials in n8n.\n\n### 2. Using Docker Environment Variables\n\nFor Docker deployments, you can pass environment variables directly to your MCP servers by prefixing them with `MCP_`:\n\n```yaml\nversion: '3'\n\nservices:\n  n8n:\n    image: n8nio\u002Fn8n\n    environment:\n      - MCP_BRAVE_API_KEY=your-api-key-here\n      - MCP_OPENAI_API_KEY=your-openai-key-here\n      - MCP_CUSTOM_SETTING=some-value\n    # other configuration...\n```\n\nThese environment variables will be automatically passed to your MCP servers when they are executed.\n\n### Example: Using Brave Search MCP Server\n\nThis example shows how to set up and use the Brave Search MCP server:\n\n1. Install the Brave Search MCP server:\n   ```bash\n   npm install -g @modelcontextprotocol\u002Fserver-brave-search\n   ```\n\n2. Configure MCP Client credentials:\n   - **Command**: `npx`\n   - **Arguments**: `-y @modelcontextprotocol\u002Fserver-brave-search`\n   - **Environment Variables**: `BRAVE_API_KEY=your-api-key` Add a variables (space comma or newline separated)\n\n3. Create a workflow that uses the MCP Client node:\n   - Add an MCP Client node\n   - Select the \"List Tools\" operation to see available search tools\n   - Add another MCP Client node\n   - Select the \"Execute Tool\" operation\n   - Choose the \"brave_search\" tool\n   - Set Parameters to: `{\"query\": \"latest AI news\"}`\n\n![Brave Search Example](.\u002Fassets\u002Fbrave-search-example.png)\n\nThe node will execute the search and return the results in the output.\n\n### Example: Multi-Server Setup with AI Agent\n\nThis example demonstrates how to set up multiple MCP servers in a production environment and use them with an AI agent:\n\n1. Configure your docker-compose.yml file:\n\n```yaml\nversion: '3'\n\nservices:\n  n8n:\n    image: n8nio\u002Fn8n\n    environment:\n      # MCP server environment variables\n      - MCP_BRAVE_API_KEY=your-brave-api-key\n      - MCP_OPENAI_API_KEY=your-openai-key\n      - MCP_SERPER_API_KEY=your-serper-key\n      - MCP_WEATHER_API_KEY=your-weather-api-key\n\n      # Enable community nodes as tools\n      - N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true\n    ports:\n      - \"5678:5678\"\n    volumes:\n      - ~\u002F.n8n:\u002Fhome\u002Fnode\u002F.n8n\n```\n\n2. Create multiple MCP Client credentials in n8n:\n\n   **Brave Search Credentials**:\n   - Command: `npx`\n   - Arguments: `-y @modelcontextprotocol\u002Fserver-brave-search`\n\n   **OpenAI Tools Credentials**:\n   - Command: `npx`\n   - Arguments: `-y @modelcontextprotocol\u002Fserver-openai`\n\n   **Web Search Credentials**:\n   - Command: `npx`\n   - Arguments: `-y @modelcontextprotocol\u002Fserver-serper`\n\n   **Weather API Credentials**:\n   - Command: `npx`\n   - Arguments: `-y @modelcontextprotocol\u002Fserver-weather`\n\n3. Create an AI Agent workflow:\n   - Add an AI Agent node\n   - Enable MCP Client as a tool\n   - Configure different MCP Client nodes with different credentials\n   - Create a prompt that uses multiple data sources\n\n![Multi-Server Setup](.\u002Fassets\u002Fmulti-server-example.png)\n\nExample AI Agent prompt:\n```\nI need you to help me plan a trip. First, search for popular destinations in {destination_country}.\nThen, check the current weather in the top 3 cities.\nFinally, find some recent news about travel restrictions for these places.\n```\n\nWith this setup, the AI agent can use multiple MCP tools across different servers, all using environment variables configured in your Docker deployment.\n\n## Operations\n\nThe MCP Client node supports the following operations:\n\n![MCP Client Operations](.\u002Fassets\u002Foperations.png)\n\n- **Execute Tool** - Execute a specific tool with parameters\n- **Get Prompt** - Get a specific prompt template\n- **List Prompts** - Get a list of available prompts\n- **List Resources** - Get a list of available resources from the MCP server\n- **List Tools** - Get a list of available tools\n- **Read Resource** - Read a specific resource by URI\n\n### Example: List Tools Operation\n\n![List Tools Example](.\u002Fassets\u002Flist-tools.png)\n\nThe List Tools operation returns all available tools from the MCP server, including their names, descriptions, and parameter schemas.\n\n### Example: Execute Tool Operation\n\n![Execute Tool Example](.\u002Fassets\u002Fexecute-tool.png)\n\nThe Execute Tool operation allows you to execute a specific tool with parameters. Make sure to select the tool you want to execute from the dropdown menu.\n\n## Using as a Tool\n\nThis node can be used as a tool in n8n AI Agents. To enable community nodes as tools, you need to set the `N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE` environment variable to `true`.\n\n### Setting the Environment Variable\n\n**If you're using a bash\u002Fzsh shell:**\n```bash\nexport N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true\nn8n start\n```\n\n**If you're using Docker:**\nAdd to your docker-compose.yml file:\n```yaml\nenvironment:\n  - N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true\n```\n\n**If you're using the desktop app:**\nCreate a `.env` file in the n8n directory:\n```\nN8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true\n```\n\n**If you want to set it permanently on Mac\u002FLinux:**\nAdd to your `~\u002F.zshrc` or `~\u002F.bash_profile`:\n```bash\nexport N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true\n```\n\nExample of an AI Agent workflow results:\n\n![AI Agent Example](.\u002Fassets\u002Fexecute-tool-result.png)\n\nAfter setting this environment variable and restarting n8n, your MCP Client node will be available as a tool in AI Agent nodes.\n\n## Compatibility\n\n- Requires n8n version 1.0.0 or later\n- Compatible with MCP Protocol version 1.0.0 or later\n- Supports both STDIO and SSE transports for connecting to MCP servers\n- SSE transport requires a server that implements the MCP Server-Sent Events specification\n\n## Resources\n\n* [n8n community nodes documentation](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fcommunity-nodes\u002F)\n* [Model Context Protocol Documentation](https:\u002F\u002Fmodelcontextprotocol.io\u002Fdocs\u002F)\n* [MCP TypeScript SDK](https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Ftypescript-sdk)\n* [MCP Transports Overview](https:\u002F\u002Fmodelcontextprotocol.io\u002Fdocs\u002Fconcepts\u002Ftransports)\n* [Using SSE in MCP](https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Ftypescript-sdk\u002Fblob\u002Fmain\u002Fsrc\u002Fclient\u002Fsse.ts)\n\n\n","n8n-nodes-mcp 是一个为 n8n 工作流自动化平台设计的自定义节点，用于与 Model Context Protocol (MCP) 服务器交互。该项目使用 TypeScript 编写，支持通过 HTTP Streamable 传输方式（推荐）或旧版的 Server-Sent Events (SSE) 与 MCP 服务器连接，从而实现资源访问、工具执行及提示功能集成。它非常适合需要在工作流中利用 AI 模型与外部工具和数据源进行标准化交互的场景，如构建能够调用多种工具的智能代理。MIT 许可证下开源，并且有详细的文档和社区贡献的教学视频支持快速上手。",2,"2026-06-11 03:47:18","high_star"]