Skip to main content
1

Get your API key

  1. Go to app.contextone.ai
  2. Sign up or log in to your account
  3. Copy your API key - you’ll need this for the next steps
2

Install Node.js and npm

Requires Node.js. Download from nodejs.org if needed.
3

Connect ContextOne to your AI agent

Choose your AI agent below and add the MCP server configuration:
  1. Open Cursor settings
  2. Go to MCP (Model Context Protocol)
  3. Add the following configuration:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
  1. Replace your-api-key-here with your API key from Step 1
  2. Restart Cursor to apply changes
  1. Open your Claude Code configuration file
  2. Add the ContextOne MCP server:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
  1. Replace your-api-key-here with your API key from Step 1
  2. Restart Claude Code
  1. Open your OpenCode settings
  2. Navigate to MCP server configuration
  3. Add this server configuration:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
  1. Replace your-api-key-here with your API key from Step 1
  2. Restart OpenCode
Add this to your Windsurf MCP configuration. See Windsurf MCP docs for more info.
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Add this to your VS Code MCP configuration. See VS Code MCP docs for more info.
{
  "mcp.servers": {
    "contextone": {
      "type": "stdio",
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
You can easily install ContextOne through the Cline MCP Server Marketplace or manually edit MCP servers configuration.
  1. Open Cline.
  2. Click the hamburger menu icon (☰) to enter the MCP Servers section.
  3. Add a new MCP server by clicking the + Add button.
  4. Add the name and server configuration from below:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Add this to your Zed settings.json. See Zed Context Server docs for more info.
{
  "context_servers": {
    "ContextOne": {
      "source": "custom",
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Add this to your Roo Code MCP configuration. See Roo Code MCP docs for more info.
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
See Gemini CLI Configuration for details.Add the following to your Gemini CLI settings.json:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Open Claude Desktop and edit your claude_desktop_config.json file. See Claude Desktop MCP docs for more info.
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
See OpenAI Codex for more information.Add the following configuration to your OpenAI Codex MCP server settings:
[mcp_servers.contextone]
args = ["@contextone/mcp@latest", "--yes"]
command = "npx"
env = { API_KEY = "your-api-key-here" }
⚠️ Windows NotesOn Windows, some users may encounter request timed out errors with the default configuration. In that case, explicitly configure the MCP server with the full path to Node.js and the installed package:
[mcp_servers.contextone]
command = "C:\\Program Files\\nodejs\\node.exe"
args = [
  "C:\\Users\\yourname\\AppData\\Roaming\\npm\\node_modules\\@contextone\\mcp-server\\dist\\index.js",
  "--transport",
  "stdio",
  "--api-key",
  "your-api-key-here"
]
Alternatively, you can use the following configuration:
[mcp_servers.contextone]
command = "cmd"
args = [
    "/c",
    "npx",
    "-y",
    "@contextone/mcp-server",
    "--api-key",
    "your-api-key-here"
]
env = { SystemRoot="C:\\Windows" }
startup_timeout_ms = 20_000
This ensures Codex CLI works reliably on Windows.⚠️ MacOS NotesOn MacOS, some users may encounter the same request timed out errors like Windows, it also can be solved tith the full path to Node.js and the installed package:
[mcp_servers.contextone]
command = "/Users/yourname/.nvm/versions/node/v22.14.0/bin/node"
args = ["/Users/yourname/.nvm/versions/node/v22.14.0/lib/node_modules/@contextone/mcp-server/dist/index.js",
  "--transport",
  "stdio",
  "--api-key",
  "your-api-key-here"
]
This ensures Codex CLI works reliably on MacOS.
See JetBrains AI Assistant Documentation for more details.
  1. In JetBrains IDEs, go to Settings -> Tools -> AI Assistant -> Model Context Protocol (MCP)
  2. Click + Add.
  3. Click on Command in the top-left corner of the dialog and select the As JSON option from the list
  4. Add this configuration and click OK
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
  1. Click Apply to save changes.
  2. The same way contextone could be added for JetBrains Junie in Settings -> Tools -> Junie -> MCP Settings
See Kiro Model Context Protocol Documentation for details.
  1. Navigate Kiro > MCP Servers
  2. Add a new MCP server by clicking the + Add button.
  3. Paste the configuration given below:
{
  "mcpServers": {
    "ContextOne": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      },
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}
  1. Click Save to apply the changes.
Use the Add manually feature and fill in the JSON configuration information for that MCP server. For more details, visit the Trae documentation.
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
For any MCP-compatible AI agent, add this server configuration:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Replace your-api-key-here with your API key from Step 1.
If you prefer to run the MCP server in a Docker container:
  1. Build the Docker Image: First, create a Dockerfile in the project root (or anywhere you prefer): 
    FROM node:18-alpine

WORKDIR /app

# Install the latest version globally
RUN npm install -g @contextone/mcp@latest

# Expose default port if needed (optional, depends on MCP client interaction)
# EXPOSE 3000

# Default command to run the server
CMD ["contextone-mcp"]
    Then, build the image using a tag (e.g., contextone-mcp). 
    docker build -t contextone-mcp .
  2. Configure Your MCP Client: Update your MCP client’s configuration to use the Docker command. Example for Cursor: 
    {
  "mcpServers": {
    "contextone": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "contextone-mcp"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
The configuration on Windows is slightly different compared to Linux or macOS.
{
  "mcpServers": {
    "contextone": {
      "command": "cmd",
      "args": ["/c", "npx", "@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Add this to your Amazon Q Developer CLI configuration. See Amazon Q Developer CLI docs for more details.
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
See Warp Model Context Protocol Documentation for details.
  1. Navigate Settings > AI > Manage MCP servers.
  2. Add a new MCP server by clicking the + Add button.
  3. Paste the configuration given below:
{
  "ContextOne": {
    "command": "npx",
    "args": ["@contextone/mcp@latest", "--yes"],
    "env": {
      "API_KEY": "your-api-key-here"
    }
  }
}
  1. Click Save to apply the changes.
Add the following configuration to the mcp section of your Copilot Coding Agent configuration file Repository->Settings->Copilot->Coding agent->MCP configuration:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
See LM Studio MCP Support for more information.
  1. Navigate to Program (right side) > Install > Edit mcp.json.
  2. Paste the configuration given below:
{
  "mcpServers": {
    "ContextOne": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
  1. Click Save to apply the changes.
  2. Toggle the MCP server on/off from the right hand side, under Program, or by clicking the plug icon at the bottom of the chat box.
You can configure ContextOne MCP in Visual Studio 2022 by following the Visual Studio MCP Servers documentation.Add this to your Visual Studio MCP config file (see the Visual Studio docs for details):
{
  "inputs": [],
  "servers": {
    "contextone": {
      "type": "stdio",
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Add this to your Crush configuration file. See Crush MCP docs for more info.
{
  "$schema": "https://charm.land/crush.json",
  "mcp": {
    "contextone": {
      "type": "stdio",
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Open the “Settings” page of the app, navigate to “Plugins,” and enter the following JSON:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
Edit your Rovo Dev CLI MCP config by running the command below -
acli rovodev mcp
Example config -
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
To configure ContextOne MCP in Zencoder, follow these steps:
  1. Go to the Zencoder menu (…)
  2. From the dropdown menu, select Agent tools
  3. Click on the Add custom MCP
  4. Add the name and server configuration from below, and make sure to hit the Install button
{
  "command": "npx",
  "args": ["@contextone/mcp@latest", "--yes"],
  "env": {
    "API_KEY": "your-api-key-here"
  }
}
See Qodo Gen docs for more details.
  1. Open Qodo Gen chat panel in VSCode or IntelliJ.
  2. Click Connect more tools.
  3. Click + Add new MCP.
  4. Add the following configuration:
{
  "mcpServers": {
    "contextone": {
      "command": "npx",
      "args": ["@contextone/mcp@latest", "--yes"],
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}
See Local and Remote MCPs for Perplexity for more information.
  1. Navigate Perplexity > Settings
  2. Select Connectors.
  3. Click Add Connector.
  4. Select Advanced.
  5. Enter Server Name: ContextOne
  6. Paste the following JSON in the text area:
{
  "args": ["@contextone/mcp@latest", "--yes"],
  "command": "npx",
  "env": {
    "API_KEY": "your-api-key-here"
  }
}
  1. Click Save.

​
Test the connection

After setup, ask your AI agent: “What can you tell me about React using ContextOne?” or “Search for Python documentation using ContextOne” If ContextOne is connected properly, your AI will access our knowledge base and provide enhanced responses with accurate documentation.

​
Next steps

Watch Video Walkthrough

Learn how to use ContextOne with a step-by-step video guide.
⌘I