Overview

Bindex MCP Server is a standalone Java 17 distribution that combines Bindex Core with the Machai MCP Server runtime. Its executable entry point is org.machanism.machai.mcp.server.McpServer; it exposes Bindex metadata retrieval, registration, schema access, and natural-language library recommendation as Model Context Protocol (MCP) tools for compatible AI clients and automation.

Bindex records describe libraries through coordinates, versions, purpose, classification, integrations, dependencies, examples, and configuration. The server can retrieve complete or GraphQL-style filtered descriptors, validate and register records supplied as JSON objects, project-relative files, or remote URLs, and recommend reusable libraries from natural-language requirements. Recommendations combine AI-generated classifications and embeddings with language, architectural-layer, similarity-score, and version-aware filtering over a MongoDB-backed repository.

The Machai MCP runtime discovers and publishes the Bindex tools and handles request routing. With no port configured, the executable communicates over STDIO; when started with --port, it serves MCP over HTTP at /mcp, with optional streamable session support. Bindex Core performs metadata normalization, persistence, retrieval, and semantic discovery, while configured GenAI and embedding services provide classification and vector generation. The Maven project packages Bindex Core and Machai MCP Server as its runtime dependencies and can assemble a self-contained executable JAR.

Supported AI providers

Bindex registration and semantic recommendations use Machai's GenAI provider abstraction. Model values use the Provider:Model form. Configure the generation or classification model through gw.model or pick.model, and select a compatible embedding model through embedding.model; embedding dimensions must match the MongoDB vector index.

• OpenAI — Use identifiers such as OpenAI:gpt-4o-mini for generation and OpenAI:text-embedding-3-small for embeddings. Set OPENAI_API_KEY; optionally set OPENAI_BASE_URL for an OpenAI-compatible endpoint.
• Anthropic — Use an identifier such as Anthropic:claude-3-5-sonnet. Set ANTHROPIC_API_KEY to an API key or authorization token; optionally set ANTHROPIC_BASE_URL. Supported models can use instructions, function tools, web search, MCP server forwarding, and prompt caching for registered tools.
• CodeMie — Use identifiers such as CodeMie:gpt-4o-mini, CodeMie:claude-3-5-sonnet, or CodeMie:text-embedding-005. Set GENAI_USERNAME and GENAI_PASSWORD; a username containing @ selects the password grant, while another value selects the client-credentials grant. Optionally override the OpenID Connect token endpoint with AUTH_URL. CodeMie obtains an OAuth 2.0 bearer token and routes supported GPT, Gemini, Claude, and embedding model families to the appropriate compatible provider, so direct OpenAI or Anthropic credentials are not required.
• Tools — Use Tools:yaml to invoke registered local Java tool callbacks from a YAML tool-call descriptor. No external AI credentials are required.
• None — Use None:disabled for a silent no-op provider or None:log for lifecycle diagnostics. These modes require no credentials and are suitable for safe defaults and tests.

Resources

• Machai platform
• Bindex MCP Server source repository
• Machai source repository
• Bindex MCP Server on Maven Central
• Bindex Core documentation
• Machai MCP Server documentation
• GenAI Client documentation