Britive MCP Server
Enables AI agents and users to interact with the Britive platform for dynamic access, query configurations, reporting, and access activity.
README
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.
Prerequisites
- Python version 3.10 or higher. Python downloads.
- Ensure you have the latest version of Git installed and access to the repository. Download git from the Git downloads.
- Any MCP client. For example: Claude desktop, VS Code Copilot
Setting up the Britive MCP Server
- Clone the GitHub repository that has the MCP server.
git clone https://github.com/britive/mcp-server.git
- Change directory to
mcp-server
cd mcp-server
- Create a virtual environment
python -m venv <virtual_env_name>
- Activate the virtual environment
-
Windows
<virtual_env_name>\Scripts\activate -
Linux
source <virtual_env_name>/bin/activate
- Install Python packages (dependencies)
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):
-
Install the PyBritive CLI if not installed. For more information, see PyBritive Documentation
-
Configure the tenant, if you have not configured it already, using the following command. To find out more about how to enter the tenant name, see PyBritive: Tenant selection logic:
pybritive configure tenant -
Log in to PyBritive:
pybritive login -
Log in using the following command if you have multiple tenants:
pybritive login --tenant=<your_tenant_name> -
Log in directs you to the Britive login page, where you can enter your credentials.
-
Modify your MCP JSON file to configure the Britive MCP.
Note:
For Windows, use backslash (\\).
For macOS/Linux, use a forward slash (/) in the path.
{
"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"
}
}
}
}
Where: <table> <tbody> <tr> <td><code>command</code></td> <td>Full path to the Python executable</td> </tr> <tr> <td><code>args</code></td> <td>Full path to the <code>britive_mcp_tools\core\mcp_runner.py</code> module.</td> </tr> <tr> <td><code>PYTHONPATH</code></td> <td>Set the Python path to the <code>mcp-server</code> directory (repository)</td> </tr> <tr> <td><code>BRITIVE_TENANT</code></td> <td>Your tenant on Britive. This tenant name must match the name used in the PyBritive CLI</td> </tr> </tbody> </table>
-
Option 2: Login using a static token:
- Generate a static token from Britive UI. For more information, see API Tokens.
- Copy the token to use in the MCP JSON file.
- Modify your MCP JSON file to configure the Britive MCP.
Note:
For Windows, use backslash (\\).
For macOS, use a forward slash (/) in the path.
{
"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"
}
}
}
}
Where: <table> <tbody> <tr> <td><code>command</code></td> <td>Full path to the Python executable</td> </tr> <tr> <td><code>args</code></td> <td>Full path to the <code>britive_mcp_tools\core\mcp_runner.py</code> module.</td> </tr> <tr> <td><code>PYTHONPATH</code></td> <td>Set the Python path to the <code>mcp-server</code> directory (repository)</td> </tr> <tr> <td><code>BRITIVE_TENANT</code></td> <td>Your tenant on Britive. Do not use the entire FQDN for the subdomain. For example, for <code>https://super-customer.test.aws.britive-corp.com</code>, use <code>super-customer.test.aws</code> as a tenant subdomain. </td> </tr> <tr> <td><code>BRITIVE_STATIC_TOKEN</code></td> <td>Static token created in the previous step</td> </tr> </tbody> </table>
Connect to the MCP server using a client application.
For more information, see Connect to Local MCP Servers.
Using On-Behalf-Of MCP Functionality
To use OBO MCP, you can following environment variable:
<table> <tbody> <tr> <td><code>BRITIVE_EMAIL</code></td> <td>The Britive email of the person you want the MCP server to impersonate</td> </tr> </tbody> </table>
If this environment variable is set, the MCP server will assume the user intends to use OBO and will take priority over non OBO MCP functionality. The BRITIVE_STATIC_TOKEN should refer to the following service identity that the user would like to perform impersonation. Currently, not all tools are supported by OBO.
List of supported OBO tools:
my_access
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.