microsoft

MCP GIPHY Server

Community microsoft
Updated

An MCP server integration with the GIPHY API

MCP GIPHY Server

Overview

This project implements a Model Context Protocol (MCP) server integration with the GIPHY API. The server allows an assistant to submit recent chat history ('context') and a search term to retrieve a list of candidate results from GIPHY and load their image data.

Features

  • Search and Retrieve: Uses the GIPHY API to search for images based on a provided search term.
  • (Future) Sampling: Employs the MCP "sampling" feature to request the assistant to choose the most appropriate image for the context.
  • Integration: The selected GIPHY image and its metadata are returned to the original assistant tool call, enabling it to be included in assistant responses to users.

Setup and Installation

Simply run:

make

To create the virtual environment and install dependencies.

Running the Server

Use the VSCode launch configuration, or run manually:

Defaults to stdio transport:

uv run -m mcp_server.start

For SSE transport:

uv run -m mcp_server.start --transport sse --port 6020

The SSE URL is:

http://127.0.0.1:6000/sse

Client Configuration

To use this MCP server in your setup, consider the following configuration:

UV - Local files

{
  "mcpServers": {
    "giphy-server": {
      "command": "uv",
      "args": ["run", "-m", "mcp_server.start"],
      "env": {
        "GIPHY_API_KEY": "YOUR_GIPHY_API_KEY"
      }
    }
  }
}

SSE

{
  "mcpServers": {
    "giphy-server": {
      "command": "http://127.0.0.1:6000/sse",
      "args": []
    }
  }
}

Ensure that GIPHY_API_KEY is set in your environment so that the server can authenticate with the GIPHY API.

MCP Server · Populars

MCP Server · New

    googleads

    Google Ads MCP Server

    MCP Server

    Community googleads
    StefanMaron

    AL MCP Server

    MCP Server

    Community StefanMaron
    vintasoftware

    Django AI Boost

    A MCP server for Django applications, inspired by Laravel Boost.

    Community vintasoftware
    idleprocesscc

    Co-Reading MCP

    A local co-reading MCP server for chunked books, reading progress, search, and margin annotations.

    Community idleprocesscc
    JasonJarvan

    Export-Zhihu-Collections

    将知乎收藏夹(公开和私密)批量导出为 Markdown 格式文件. 支持配置收藏夹列表并批量下载, 支持基于URL自动去重, 支持下载专栏和图片, 支持自定义保存路径, 支持调试和错误日志. **同时提供 MCP Server**,可被 AI Agent (如 Claude Code) 直接调用,为大模型提供保存知乎收藏夹的能力。

    Community JasonJarvan