mcp-optimizer
Verified Safeby StacklokLabs
Overview
Acts as an intelligent intermediary MCP server providing semantic tool discovery, caching, and unified access to multiple MCP servers through a single endpoint for AI clients.
Installation
mcp-optimizerEnvironment Variables
- RUNTIME_MODE
- ALLOWED_GROUPS
- ASYNC_DB_URL
- DB_URL
- K8S_API_SERVER_URL
- K8S_NAMESPACE
- K8S_ALL_NAMESPACES
- EMBEDDING_MODEL_NAME
- MAX_TOOL_RESPONSE_TOKENS
- ENABLE_DYNAMIC_INSTALL
- FASTEMBED_CACHE_PATH
- TIKTOKEN_CACHE_DIR
Security Notes
The database operation classes (`BaseServerOps`, `BaseToolOps`) use f-strings to construct SQL queries with table names, which is a fragile pattern that could lead to SQL injection if table names were ever derived from user input. Although the code includes explicit warnings and attempts to enforce hardcoded table names via abstract properties, this architectural choice demands extreme caution. FTS queries are sanitized. No direct hardcoded secrets or 'eval' statements were found. In-cluster Kubernetes authentication is handled securely via service accounts.
Similar Servers
klavis
Creates an AI agent that uses Klavis Strata to interact with Gmail and YouTube through MCP, demonstrating how to summarize a YouTube video and email the summary.
mcphub
The MCPHub acts as a centralized gateway for managing and orchestrating various Model Context Protocol (MCP) servers and OpenAPI-compatible services. It provides a unified API, OAuth 2.0 authorization, user management, and AI-powered 'smart routing' for dynamic tool discovery and invocation.
toolhive
Manages, secures, and integrates Model Context Protocol (MCP) servers across local development and Kubernetes environments, facilitating secure deployment, authentication, authorization, and workflow orchestration for AI/ML agents.
MCPJungle
A self-hosted gateway and registry for Model Context Protocol (MCP) servers, allowing AI agents to discover and consume tools from a central location.