Implement a standardized MCP server for Glean search and chat AI capabilities
@gleanwork/mcp-server is a Model Context Protocol (MCP) server implementation designed to enhance and integrate AI applications with Glean's robust content search and chat functionalities. This MCP server adheres to the MCP specification, providing a standardized interface that various AI clients can use to leverage Glean’s advanced capabilities in a seamless and interoperable manner.
@gleanwork/mcp-server offers several key features and MCP capabilities:
@gleanwork/mcp-server is built to adhere strictly to the MCP protocol specification, enabling seamless communication between AI applications and Glean's content search and chat features. The server leverages REST API calls for interacting with Glean’s services, providing a robust and flexible solution.
graph TD
A[AI Application] -->|MCP Client| B[MCP Server]
B --> C[Glean Search & Chat API]
C --> D[Data Source/Tool]
style A fill:#e1f5fe
style C fill:#f3e5f5
style D fill:#ffffff
graph TD
G[Global Configuration] --> H[MCP Server]
I[Data Source/Tool] --> J[Cached Data]
K[Cached Data] --> L[MCP Client]
M[MCP Client] --> N[AI Application]
style G fill:#f5e3fb
style H fill:#fce8d7
style I fill:#b0e0e6
style J fill:#d1ffee
style K fill:#bdegne
style L fill:#e0f2ff
style M fill:#f5ebde
To get started, it’s essential to configure your Glean API credentials and ensure that the environment is properly set up. Here are the steps to follow:
export GLEAN_SUBDOMAIN=your_subdomain
export GLEAN_API_TOKEN=your_api_token
npx @gleanwork/mcp-server configure --client [Client Name] --token your_api_token --domain your_subdomain
Alternatively, you can use an environment file to set up the configuration:
npx @gleanwork/mcp-server configure --client [Client Name] --env path/to/.env.glean
The .env.glean
file should contain:
GLEAN_SUBDOMAIN=your_subdomain
GLEAN_API_TOKEN=your_api_token
@gleanwork/mcp-server is designed to be compatible with multiple MCP clients, including Claude Desktop, Continue, Cursor, and others. Here’s a compatibility matrix showcasing supported features:
MCP Client | Resources | Tools | Prompts | Status |
---|---|---|---|---|
Claude Desktop | ✅ | ✅ | ✅ | Full Support |
Continue | ✅ | ✅ | ✅ | Full Support |
Cursor | ❌(limited) | ✅ | ❌ | Tools Only |
The performance and compatibility of @gleanwork/mcp-server have been rigorously tested to ensure optimal functionality. The server is designed to handle high volumes of requests while maintaining low latency, making it suitable for real-time applications.
Advanced users can configure various aspects of the MCP server for enhanced security and performance:
chat
, search
) are used..env.glean
file that contains necessary credentials and domain information.Contributions to @gleanwork/mcp-server are highly valued. Developers can contribute by following the guidelines outlined in CONTRIBUTING.md.
For detailed information and additional resources, refer to:
By leveraging @gleanwork/mcp-server, users can integrate advanced AI capabilities into their applications seamlessly and efficiently.
RuinedFooocus is a local AI image generator and chatbot image server for seamless creative control
Simplify MySQL queries with Java-based MysqlMcpServer for easy standard input-output communication
Learn to set up MCP Airflow Database server for efficient database interactions and querying airflow data
Build stunning one-page websites track engagement create QR codes monetize content easily with Acalytica
Explore CoRT MCP server for advanced self-arguing AI with multi-LLM inference and enhanced evaluation methods
Access NASA APIs for space data, images, asteroids, weather, and exoplanets via MCP integration