This section provides guidance on integrating various AI agent frameworks with the Model Context Protocol (MCP) Gateway. MCP enables agents to dynamically discover and utilize tools across multiple servers, enhancing their capabilities and flexibility.
🧠 Supported Agent Frameworks
Using ContextForge (Agent frameworks as MCP clients)
LangChain: Utilize MCP tools within LangChain agents using the langchain-mcp-adapters package.
LangGraph: Integrate MCP tools into LangGraph agents for advanced workflow orchestration.
CrewAI: Connect CrewAI agents to MCP servers using the crewai-tools library.
Bee Agent Framework: Leverage MCP tools within the Bee Agent Framework for scalable agent deployments.
AutoGen: Integrate MCP tools with AutoGen agents using the autogen-ext-mcp package.
LlamaIndex: Incorporate MCP tools into LlamaIndex workflows for enhanced data retrieval and question answering.
OpenAI Agents SDK: Utilize MCP tools within OpenAI's Agents SDK for building AI agents with standardized tool access.
Semantic Kernel: Connect Semantic Kernel agents to MCP servers for enriched context and tool integration.
A2A (Agent-to-Agent) Integration (External agents in ContextForge)
A2A Integration: Complete guide to registering external AI agents in ContextForge
External AI Agents: Register external AI agents (OpenAI, Anthropic, custom) as A2A agents in the gateway
Tool Exposure: A2A agents are automatically exposed as MCP tools for other agents to discover and use
Protocol Support: Supports JSONRPC, custom protocols, and multiple authentication methods
Admin Management: Full admin UI for registering, testing, and managing external agents
Virtual Server Integration: Associate A2A agents with virtual servers for organized tool catalogs
🔍 Overview
Each integration guide includes:
Installation Instructions: Step-by-step setup for the respective agent framework.
Configuration Details: How to connect the agent to ContextForge, including authentication and transport options.
Usage Examples: Sample code demonstrating how to invoke MCP tools within the agent's workflow.
Additional Resources: Links to official documentation and repositories for further reference.
1---2name: 468-index-6da5357e3description: Agent Integrations4---5# Agent Integrations67This section provides guidance on integrating various AI agent frameworks with the Model Context Protocol (MCP) Gateway. MCP enables agents to dynamically discover and utilize tools across multiple servers, enhancing their capabilities and flexibility.89---1011## 🧠 Supported Agent Frameworks1213### Using ContextForge (Agent frameworks as MCP clients)14- [LangChain](langchain.md): Utilize MCP tools within LangChain agents using the `langchain-mcp-adapters` package.15- [LangGraph](langgraph.md): Integrate MCP tools into LangGraph agents for advanced workflow orchestration.16- [CrewAI](crewai.md): Connect CrewAI agents to MCP servers using the `crewai-tools` library.17- [Bee Agent Framework](bee.md): Leverage MCP tools within the Bee Agent Framework for scalable agent deployments.18- [AutoGen](autogen.md): Integrate MCP tools with AutoGen agents using the `autogen-ext-mcp` package.19- [LlamaIndex](llamaindex.md): Incorporate MCP tools into LlamaIndex workflows for enhanced data retrieval and question answering.20- [OpenAI Agents SDK](openai-sdk.md): Utilize MCP tools within OpenAI's Agents SDK for building AI agents with standardized tool access.21- [Semantic Kernel](semantic-kernel.md): Connect Semantic Kernel agents to MCP servers for enriched context and tool integration.2223### A2A (Agent-to-Agent) Integration (External agents in ContextForge)24- **[A2A Integration](a2a.md)**: Complete guide to registering external AI agents in ContextForge25- **External AI Agents**: Register external AI agents (OpenAI, Anthropic, custom) as A2A agents in the gateway26- **Tool Exposure**: A2A agents are automatically exposed as MCP tools for other agents to discover and use27- **Protocol Support**: Supports JSONRPC, custom protocols, and multiple authentication methods28- **Admin Management**: Full admin UI for registering, testing, and managing external agents29- **Virtual Server Integration**: Associate A2A agents with virtual servers for organized tool catalogs3031---3233## 🔍 Overview3435Each integration guide includes:3637- **Installation Instructions**: Step-by-step setup for the respective agent framework.38- **Configuration Details**: How to connect the agent to ContextForge, including authentication and transport options.39- **Usage Examples**: Sample code demonstrating how to invoke MCP tools within the agent's workflow.40- **Additional Resources**: Links to official documentation and repositories for further reference.4142---4344## 📚 Additional Resources4546- [Model Context Protocol Overview](https://modelcontextprotocol.io/)47- [ContextForge Documentation](../index.md)4849---
Run npx skillmds@latest add tools-only/468-index-6da5357e in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Agent Integrations It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tools-only (@tools-only) published this skill. Their other Agent Skills are listed on their SkillMD profile.
tools-only