What is the Greptile MCP Server?

The Greptile MCP (Model Context Protocol) Server is a tool that enables AI agents to interact with codebases by providing capabilities to index, query, and search code repositories. It acts as a bridge between AI models and code, allowing them to understand and analyze code effectively.

What is an MCP (Model Context Protocol)?

MCP is an open protocol that standardizes how applications provide context to LLMs.

What are the key features of the Greptile MCP Server?

The key features include:

• index_repository: Indexes a repository for code search and querying.
• query_repository: Queries repositories to get answers with code references using natural language.
• search_repository: Searches repositories for relevant files without generating a full answer.
• get_repository_info: Gets information about an indexed repository, such as status and metadata.

What are the prerequisites for using the Greptile MCP Server?

The prerequisites include:

• Python 3.12+
• Greptile API Key
• GitHub or GitLab Personal Access Token (PAT) with repo permissions
• Docker (recommended for deployment)

How do I install the Greptile MCP Server?

You can install the server using either pip or Docker. Detailed instructions are provided in the documentation.

What is Smithery deployment and how is it used with the Greptile MCP Server?

Smithery is a platform for deploying and managing AI agents. The Greptile MCP Server supports deployment via Smithery, with a smithery.yaml configuration file included in the project root.

How do I configure the Greptile MCP Server?

Configuration is done through environment variables, such as GREPTILE_API_KEY, GITHUB_TOKEN, and GREPTILE_BASE_URL. These can be set in a .env file.

What transport methods are supported for integrating with MCP clients?

The server supports SSE (Server-Sent Events) and Stdio transport methods. Configuration examples for both are provided in the documentation.

How do I integrate the Greptile MCP Server with Claude.ai?

The documentation provides an integration example demonstrating how to use the server with Claude.ai via the Anthropic API, including steps for querying code and formatting context for Claude.

What is UBOS, and how does the Greptile MCP Server integrate with it?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. The Greptile MCP Server integrates with UBOS to provide code search and querying capabilities to AI agents, enhancing their ability to interact with and understand codebases within the UBOS environment.