Skip to main content

An MCP server for integrating Giphy into AI agents.

Project description

Giphy MCP Server

CI PyPI version

An MCP (Model Context Protocol) server that allows AI agents to search and retrieve GIFs using the Giphy API. This provides a rich way for agents to express humor, reactions, or find relevant visual context.

Prerequisites

Installation

For general use, install the package via pip:

pip install giphy-mcp

For development:

  1. Clone the repository:
    git clone https://github.com/Szatek/giphy-mcp-server.git
    cd giphy-mcp-server
    
  2. Create a virtual environment and install in editable mode:
    python -m venv venv
    # On Windows
    .\venv\Scripts\activate
    # On Linux/macOS
    source venv/bin/activate
    
    pip install -e ".[dev]"
    

Configuration

The server requires a Giphy API Key to function. It reads this from the GIPHY_API_KEY environment variable.

You can configure this by:

  1. Creating a .env file in the project root:
    GIPHY_API_KEY=your_api_key_here
    
  2. Or by passing it directly via your MCP client's configuration.

Available Tools

  • search_gifs
    • Description: Search for GIFs using the Giphy API.
    • Parameters:
      • query (string): The search term to find GIFs for.
      • limit (int, optional): The maximum number of GIFs to return (default: 5).
      • rating (string, optional): Filters results by specified rating (default: 'g').

Example Use Case (Agent Interaction)

When this server is registered with an AI agent (like Claude Desktop or Cursor), the agent can autonomously use it to attach GIFs to its responses.

User: "Can you celebrate that we finally deployed to production?"

Agent (Internal Thought): The user wants to celebrate. A celebratory GIF would be perfect here. I will use the search_gifs tool with the query "celebrate".

Agent (Tool Call):

{
  "name": "search_gifs",
  "arguments": {
    "query": "celebrate",
    "limit": 1
  }
}

Agent (Response): "Woohoo! That's awesome news! Here's a celebratory GIF to match the mood:

celebratory GIF"

Antigravity AI Agent Integration & Skills

This repository includes custom Agent Skills located in the .agents/skills directory designed for the Antigravity AI framework (or other compatible systems).

Included Skills

  • Giphy Chat Enhancer: Instructs your AI agent to embed an appropriate GIF during special conversational events (successes, errors, debugging milestones), injecting a fun, nerdy communication style into your interactions.
  • Giphy Documentation Enhancer: Instructs the agent to proactively embed tasteful Giphy images when generating or updating README.md files and user documentation.

Auto-Installation

The skills are written with internal logic that instructs the AI agent to recognize if it lacks the search_gifs tool. If the tool is missing, the agent will autonomously:

  1. Run pip install giphy-mcp
  2. Configure itself securely by modifying its $HOME/.gemini/antigravity/mcp_config.json configuration file, adding the following snippet:
"mcpServers": {
  "giphy": {
    "command": "giphy-mcp",
    "args": [],
    "env": {
      "GIPHY_API_KEY": "your_api_key_here"
    }
  }
}

Using with built-in MCP Clients

To use this with an MCP client like Claude Desktop, add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "giphy": {
      "command": "giphy-mcp",
      "args": [],
      "env": {
        "GIPHY_API_KEY": "your_api_key_here"
      }
    }
  }
}

Note: You may need to specify the absolute path to the giphy-mcp executable if it's not in your system's PATH.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

giphy_mcp-1.0.0.tar.gz (11.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

giphy_mcp-1.0.0-py3-none-any.whl (5.6 kB view details)

Uploaded Python 3

File details

Details for the file giphy_mcp-1.0.0.tar.gz.

File metadata

  • Download URL: giphy_mcp-1.0.0.tar.gz
  • Upload date:
  • Size: 11.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for giphy_mcp-1.0.0.tar.gz
Algorithm Hash digest
SHA256 b24f48ffe8b4705aad0a38b200c88f59b9529613627127bc96159458d6ed58b2
MD5 c725a3085e250d36cb18ab20a75fb3a1
BLAKE2b-256 1d7a6c36aa07ef53cb840a182eba6c90392813f317de8e589af912d1117d5721

See more details on using hashes here.

Provenance

The following attestation bundles were made for giphy_mcp-1.0.0.tar.gz:

Publisher: publish.yml on Szatek/giphy-mcp-server

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file giphy_mcp-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: giphy_mcp-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 5.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for giphy_mcp-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fe7beb79bb0e373161038e1713164bcd820ffe8f8164718953e7ee15505b379a
MD5 d2a2b6859a8ef04ce6c83bb182e2e8ed
BLAKE2b-256 6b73c7878a7c1989d77c9786f698aa74dfd4c20ecaf69666b24a3884389c8206

See more details on using hashes here.

Provenance

The following attestation bundles were made for giphy_mcp-1.0.0-py3-none-any.whl:

Publisher: publish.yml on Szatek/giphy-mcp-server

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page