--- title: "Britive MCP Server" slug: "setting-up-mcp-server" updated: 2026-02-26T12:53:10Z published: 2026-02-26T12:53:10Z canonical: "docs.britive.com/setting-up-mcp-server" --- > ## Documentation Index > Fetch the complete documentation index at: https://docs.britive.com/llms.txt > Use this file to discover all available pages before exploring further. # Britive MCP Server Britive's MCP Server enables AI agents and users to interact with the Britive platform. Britive's MCP server exposes several tools that enable users and AI agents to interact with the Britive platform for dynamic access, query configurations, reporting, and access activity. To learn more about MCPs, see [Get Started with MCP](https://modelcontextprotocol.io/docs/getting-started/intro). There are two ways to connect to Britive's MCP server: - [Connect to Remote MCP Servers](/v1/docs/setting-up-mcp-server#connect-to-remote-mcp-servers) [](/v1/docs/setting-up-mcp-server#connect-to-local-mcp-servers) - [Connect to Local MCP Servers](/v1/docs/setting-up-mcp-server#connect-to-local-mcp-servers) ## Connect to Remote MCP Servers ### Prerequisite - Any MCP client. For example, Claude desktop and VS Code Copilot. ### Setting up the Britive MCP Server The following steps show an example of setting up a Britive MCP server using Claude desktop. 1. Create a custom connector using the Claude desktop: 1. Enter the name of the connector. 2. Enter the remote MCP server URL. Make sure the endpoint has */mcp* at the end. For example: *https://<>.britive-app.com/mcp*. 2. Connect to the custom connector. It redirects to the Britive tenant login screen. 3. Log into the tenant using SSO login or using a username/password combination. 4. After a successful connection, the remote server’s resources and prompts become available in the Claude conversations. You can use Britive actions like "list AWS profiles," "list my resources," etc., in the conversation. Administrators can use actions like profile checkout, generate reports, etc. For more information about creating custom connectors and other configurations, see [Connect to Remote MCP Servers](https://modelcontextprotocol.io/docs/develop/connect-remote-servers#connecting-to-a-remote-mcp-server). ## Connect to Local MCP Servers ### Prerequisites - Python version 3.10 or higher. Download from [Python downloads](https://www.python.org/downloads/). - Ensure you have the latest version of Git installed and access to the repository. Download Git from the [git downloads](https://git-scm.com/downloads). - Any MCP client. For example, Claude desktop and VS Code Copilot. ### Setting up the Britive MCP Server 1. Clone the GitHub repository that has the MCP server. ```plaintext git clone https://github.com/britive/mcp-server.git ``` 2. heChange directory to *mcp-server:* ```shell cd mcp-server ``` 3. Create a virtual environment: ```plaintext python -m venv ``` 4. Activate virtual environment: 1. Windows: ```shell \Scripts\activate ``` 2. macOS/Linux: ```shell source /bin/activate ``` 1. Install Python packages (dependencies): ```shell pip install -r requirements.txt ``` ### Configuring your MCP client and Authentication Authentication to the Britive platform can be performed using the Britive CLI or a static token: - Option 1: CLI login using PyBritive (Recommended): 1. Install the PyBritive CLI if it is not already installed. For more information, see [PyBritive Documentation](https://britive.github.io/python-cli/). 2. Configure the tenant, if it has not already been configured, using the following command. To find out more about how to enter the tenant name, see [PyBritive: Tenant selection logic](https://britive.github.io/python-cli/#tenant-selection-logic). ```shell pybritive configure tenant ``` 3. Log in to pyBritive: ```shell pybritive login ``` 4. Log in using the following command if you have multiple tenants: ```shell pybritive login --tenant= ``` 5. Log in directs you to the Britive login page, where you can enter your credentials. 6. Modify your MCP JSON file to configure the Britive MCP. The MCP JSON file may be located at different locations depending on your MCP client and how it was installed. - Windows: If you are using the Claude desktop as your MCP client, the JSON file might be at this location: *%APPDATA%\Claude\claude_desktop_config.json.* ```shell {  "servers": {    "britive": {      "command": "C:\\Users\\YourName\\mcp-server\\venv\\Scripts\\python.exe",      "args": [        "C:\\Users\\YourName\\mcp-server\\britive_mcp_tools\\core\\mcp_runner.py"      ],      "env": {        "PYTHONPATH": "C:\\Users\\YourName\\mcp-server",        "BRITIVE_TENANT": "your_tenant_name",      }    }  } } ``` - macOS/Linux: If you are using the Claude desktop on macOS as your MCP client, the JSON file might be at this location: *~/Library/Application Support/Claude/claude_desktop_config.json.* ```shell {  "servers": {    "britive": {      "command": "/user/local/bin/python",      "args": [        "/Users/YourName/mcp-server/britive_mcp_tools/core/mcp_runner.py"      ],      "env": {        "PYTHONPATH": "/Users/YourName/mcp-server",        "BRITIVE_TENANT": "your_tenant_name",      }    }  } } ``` - where: - *command*: Full path to the Python executable - *args*: Full path to the *britive_mcp_tools\core\mcp_runner.py* - *PYTHONPATH*: Set the Python path to the *mcp-server* directory (repository) - *BRITIVE_TENANT*: Your tenant on Britive. This tenant name must match the name used in the PyBritive CLI - Option 2: Log in using a static token: ### Connecting to the MCP server using a client application For more information, see [Connect to Local MCP Servers](https://modelcontextprotocol.io/docs/develop/connect-local-servers). 1. Generate a static token from the Britive UI. For more information, see [API Tokens](/v1/docs/api-tokens-1). 2. Copy the token to use in the MCP JSON file. 3. Modify your MCP JSON file to configure the Britive MCP. The MCP JSON file may be located at different locations depending on your MCP client and how it was installed. - Windows: If you are using the Claude desktop as your MCP client, the JSON file might be at this location: *%APPDATA%\Claude\claude_desktop_config.json* ```shell {  "servers": {    "britive": {      "command": "C:\\Users\\YourName\\mcp-server\\venv\\Scripts\\python.exe",      "args": ["C:\\Users\\YourName\\mcp-server\\britive_mcp_tools\\core\\mcp_runner.py"      ],      "env": {        "PYTHONPATH": "C:\\Users\\YourName\\mcp-server",        "BRITIVE_TENANT": "your_tenant_name",        "BRITIVE_STATIC_TOKEN": "your_static_token_here"      }    }  } } ``` - macOS/Linux: If you are using the Claude desktop on macOS as your MCP client, the JSON file might be at this location: *~/Library/Application Support/Claude/claude_desktop_config.json.* ```shell {  "servers": {    "britive": {      "command": "/user/local/bin/python",      "args": [        "/Users/YourName/mcp-server/britive_mcp_tools/core/mcp_runner.py"      ],      "env": {        "PYTHONPATH": "/Users/YourName/mcp-server",        "BRITIVE_TENANT": "your_tenant_name",        "BRITIVE_STATIC_TOKEN": "your_static_token_here"      }    }  } } ``` - where: - command: Full path to the Python executable - args: Full path to the *britive_mcp_tools\core\mcp_runner.py* module - PYTHONPATH: Set the Python path to the *mcp-server* directory (repository) - BRITIVE_TENANT: Your tenant on Britive. Do not use the entire FQDN for the subdomain. For example, for *https://super-customer.test.aws.britive-corp.com*, use *super-customer.test.aws* as a tenant subdomain. - BRITIVE_STATIC_TOKEN: Static token created in the previous step