How to integrate Giphy MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Giphy Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Giphy to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Giphy agent that can find trending cat gifs for today, get sticker variations for smile emoji, list gifs in the 'reactions' category, fetch metadata for gif by id through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Giphy account through Composio's Giphy MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Giphy
  • Configure an AI agent that can use Giphy as a tool
  • Run a live chat session where you can ask the agent to perform Giphy operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Giphy MCP server, and what's possible with it?

The Giphy MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Giphy account. It provides structured and secure access to the world’s largest GIF and sticker library, so your agent can search for GIFs, fetch trending categories, retrieve GIF metadata, and even track analytics on user interactions automatically.

  • GIF and sticker search and retrieval: Instantly have your agent fetch GIFs and stickers by ID, category, or emoji for any topic or mood you need.
  • Browse trending categories and curated content: Let your agent pull the latest GIF categories and browse curated collections to suggest the perfect GIF for any occasion.
  • Access detailed GIF and sticker metadata: Retrieve comprehensive information about specific GIFs, stickers, or even groups of items by their unique IDs.
  • Emoji and sticker variation discovery: Explore emoji GIFs and their creative variations, making it easy to add fun reactions or flair to your app or chat.
  • User interaction analytics logging: Track and register when users view, click, or share GIFs, enabling smarter personalization and reporting within your workflows.

Supported Tools & Triggers

Tools
Giphy Analytics RegisterTool to register user interactions (view, click, send) with a GIF for analytics.
Emoji VariationsTool to fetch variations for a specific emoji.
Get GIF by IDTool to fetch GIF metadata by its unique ID.
Get GIFs by IDsTool to fetch metadata for multiple GIFs by their IDs.
Get Sticker by IDTool to fetch sticker metadata by its unique ID.
Get Stickers by IDsTool to fetch metadata for multiple stickers by their IDs.
GIPHY CategoriesTool to fetch a list of GIF categories on GIPHY.
GIPHY: Get Category by IDTool to fetch metadata for a GIF category by its unique ID.
GIPHY: Category GIFsTool to fetch GIFs associated with a specific GIF category.
GIPHY EmojiTool to fetch GIPHY emoji GIF objects.
Get Related TagsTool to fetch tags related to a specified tag.
GIPHY: Tag SearchTool to search GIPHY's tag library for autocomplete suggestions.
GIPHY Trending TagsTool to fetch the most popular search terms (tags) on GIPHY.
GIPHY Translate StickerTool to translate a term or phrase into a single sticker using GIPHY’s translation algorithm.
Get Trending StickersTool to fetch trending stickers.
Giphy Random GIFTool to fetch a random GIF from Giphy.
Giphy Random StickerTool to fetch a single random sticker.
GIPHY: Search GIFsTool to search GIPHY's GIF library.
GIPHY: Search StickersTool to search GIPHY's sticker library.
GIPHY: Random TagTool to fetch a single random tag from Giphy.
GIPHY Trending GIFsTool to fetch trending GIFs from GIPHY.
Giphy Upload GIFTool to upload a GIF or video file to GIPHY.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Giphy project
  • Some knowledge of Python or Typescript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Giphy.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Giphy Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["giphy"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only giphy.
  • The router checks the user's Giphy connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Giphy.
  • This approach keeps things lightweight and lets the agent request Giphy tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Giphy. "
        "Help users perform Giphy operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Giphy and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Giphy operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Giphy.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Giphy and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["giphy"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Giphy. "
        "Help users perform Giphy operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Giphy MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Giphy.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Giphy MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Giphy MCP with Claude Agent SDK

Google ADK

Google ADK

Use Giphy MCP with Google ADK

LangChain

LangChain

Use Giphy MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Giphy MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Giphy MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Giphy MCP with LlamaIndex

CrewAI

CrewAI

Use Giphy MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Giphy MCP?

With a standalone Giphy MCP server, the agents and LLMs can only access a fixed set of Giphy tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Giphy and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Giphy tools.

Can I manage the permissions and scopes for Giphy while using Tool Router?

Yes, absolutely. You can configure which Giphy scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Giphy data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free