mcp_server
by take566
Overview
A collection of Model Context Protocol (MCP) servers and development tools to extend AI assistant capabilities by providing access to external services and system interactions.
Installation
cd mcp_servers/gdrive-mcp && npm install && npm run build && npm startEnvironment Variables
- GDRIVE_OAUTH_PATH
- GDRIVE_CREDENTIALS_PATH
- OLLAMA_HOST
- NOTION_API_KEY
- OPENAPI_MCP_HEADERS
- GITHUB_PERSONAL_ACCESS_TOKEN
- BRAVE_API_KEY
- GOOGLE_CLIENT_EMAIL
- GOOGLE_PRIVATE_KEY
- GA_PROPERTY_ID
- SERENA_PROJECT_PATH
- CIPHER_WORKSPACE
- OPENAI_API_KEY
- CIPHER_EMBEDDER
Security Notes
The `gcp-oauth.keys.json` file contains hardcoded Google Cloud `client_id` and `client_secret`, which is a severe security vulnerability. Additionally, various `claude_desktop_config.json` files contain hardcoded `key` values (e.g., for `@smithery/cli` based MCPs) that appear sensitive. The use of `exec` in `gdrive-mcp` for opening a browser is a potential, though currently limited, command injection risk. Relying on local file paths in configuration for executing MCP servers (e.g., `node.exe` paths) introduces a risk if these configuration files or the local environment are compromised.
Similar Servers
awesome-mcp-devtools
This repository provides a curated list of developer tools, SDKs, frameworks, libraries, utilities, and resources for working with Model Context Protocol (MCP) servers.
mcp-servers
Provides a curated collection of Model Context Protocol (MCP) server configurations to enable AI agents to interact with various developer tools and services.
mcp-registry
This repository serves as a centralized, community-maintained registry for Model Context Protocol (MCP) servers, providing structured installation configurations to facilitate discovery and integration for MCP clients and hubs.
toolhive-registry
Connects to Elasticsearch instances to query data, manage indices, and retrieve metadata for search and analytics.