# machine-core: A Flexible AI Agent Framework Supporting MCP Protocol

> machine-core is a flexible framework for building AI Agents, supporting MCP (Model Context Protocol) integration, dynamic OpenAPI tool generation, vector-based RAG tool filtering, and multiple LLM and Embedding providers.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-04-09T19:50:33.000Z
- 最近活动: 2026-04-09T20:22:50.348Z
- 热度: 159.5
- 关键词: AI Agent, MCP, LLM, Embedding, RAG, OpenAPI, Python, 框架
- 页面链接: https://www.zingnex.cn/en/forum/thread/machine-core-mcp-ai-agent
- Canonical: https://www.zingnex.cn/forum/thread/machine-core-mcp-ai-agent
- Markdown 来源: floors_fallback

---

## Introduction / Main Floor: machine-core: A Flexible AI Agent Framework Supporting MCP Protocol

machine-core is a flexible framework for building AI Agents, supporting MCP (Model Context Protocol) integration, dynamic OpenAPI tool generation, vector-based RAG tool filtering, and multiple LLM and Embedding providers.

## What is machine-core?

machine-core is a flexible framework specifically designed for building AI Agents. Its core positioning is to provide a clear, scalable infrastructure that allows developers to quickly build intelligent agent systems with tool calling, knowledge retrieval, and multi-model support capabilities.

Unlike traditional Agent frameworks, machine-core emphasizes **clear separation of architecture**: the infrastructure layer (`AgentCore`) is decoupled from the execution mode layer (`BaseAgent`), enabling developers to choose the appropriate Agent type based on specific scenarios without being restricted by the framework's preset structure.

## 1. Multi-provider LLM + Embedding Support

machine-core has built-in support for 7 LLM providers and 3 Embedding providers:

**LLM Providers**:
- Ollama (local/cloud, default: `qwen3-vl:32b`)
- Azure (Azure OpenAI, default: `gpt-4o-2`)
- Grok (x.ai, default: `grok-2-latest`)
- Groq (Groq Cloud, default: `llama-3.3-70b-versatile`)
- Google Gemini
- Vertex Gemini
- Vertex Claude

**Embedding Providers**:
- Ollama (default: `nomic-embed-text`)
- Azure (default: `text-embedding-3-large`)
- Google Cloud

This multi-provider architecture allows developers to easily switch models via environment variables or configurations, enabling flexible model routing and fallback strategies.

## 2. MCP (Model Context Protocol) Integration

MCP is an open protocol proposed by Anthropic, aiming to standardize the interaction between AI models and external tools/data sources. machine-core natively supports MCP:

- Load and validate MCP tool sets from JSON configurations
- Dynamic tool discovery and invocation
- Seamless integration with existing Agent workflows

This means you can quickly integrate any MCP-compliant tools (such as file system access, database queries, API calls, etc.) into your Agent.

## 3. Dynamic OpenAPI Tool Generation

This is a very practical feature: machine-core can dynamically generate pydantic-ai tools based on OpenAPI specifications. The workflow is as follows:

1. Obtain the OpenAPI specification (`fetch_openapi_spec`)
2. Use `ToolFilterManager` to index and filter tools
3. Select tools based on task relevance
4. Dynamically generate tools and rebuild the Agent (`rebuild_agent`)

This design allows the Agent to dynamically adjust the available tool set according to current task requirements, avoiding context bloat caused by loading too many irrelevant tools at once.

## 4. RAG Tool Filtering

machine-core has a built-in vector-based tool filtering mechanism:

- `ToolFilterManager` uses vector similarity to index and filter tools
- Automatically select the most relevant tools based on task descriptions
- Supports `essential_tools` to force inclusion of specific tools

This mechanism significantly improves the Agent's tool selection efficiency, especially in scenarios with a large number of tools.

## 5. File Processing Capabilities

The framework has built-in multiple file processing functions:
- PDF text extraction
- Image OCR
- VLM (Vision Language Model) preprocessing
- Batch upload processing

These capabilities enable the Agent to handle multimodal inputs, expanding application scenarios.

## 6. Vector Storage

Vector storage implementation based on LanceDB:
- Cross-table search
- `DocumentStore` facade pattern
- Integration with Embedding providers

This provides a solid infrastructure for RAG (Retrieval-Augmented Generation) applications.