MCP Server for Gravatar

by andrewdmontgomery

111 downloads
Not rated
GitHub

About

MCP Server for Gravatar is a stdio-based Model Context Protocol (MCP) server that provides access to Gravatar profile and avatar data. It allows MCP‑aware clients such as Claude Desktop or custom IDE plugins to discover and invoke tools for fetching Gravatar profiles and avatars.

Details

Author
andrewdmontgomery
Downloads
111
Categories
Other

- Fetch Gravatar profile by email or SHA256 hash
- Retrieve specific profile fields
- List user avatars and fetch avatar image bytes
- Works over stdio for easy MCP integration

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MCP Server for Gravatar
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install dependencies with uv sync, then run the server via uv run mcp-server-gravatar or using uvx. To integrate with Claude Desktop, add a JSON entry to claude_desktop_config.json using either uvx or a git URL. Optionally set the GRAVATAR_API_TOKEN environment variable for authentication.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp server for gravatar": {
            "mcp-server-gravatar": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

McpServers

{
    "mcp-server-gravatar": {
        "command": "uv",
        "args": [
            "sync"
        ]
    }
}

MCP Server for Gravatar

A stdio-based Model Context Protocol (MCP) server that provides access to Gravatar profile and avatar data. Clients (e.g., Claude Desktop, custom IDE plugins) can discover and invoke tools via MCP to fetch Gravatar profiles and avatars.

Features

- Fetch Gravatar profile by email or SHA256 hash
- Retrieve specific profile fields
- List user avatars and fetch avatar image bytes
- Works over stdio for easy integration with MCP-aware clients

Prerequisites

- Python 3.10 or later
- uv CLI tool installed (provides uv sync and uv run)
- (Optional) Docker, if you need to regenerate the OpenAPI client via make generate

Setup

1. Clone the repository

   git clone https://github.com/andrewdmontgomery/mcp-server-gravatar.git
   cd mcp-server-gravatar
   

2. Install dependencies

   uv sync
   

This will install all Python dependencies specified in pyproject.toml into your active virtual environment.

Regenerating the OpenAPI client

(if you’ve updated openapi.yaml) > [!CAUTION] > Regenerating the client will cause problems. There are manual changes that have been applied to the generated code in order to fix issues. > If you re-generate the openapi_client, those changes should be retained. Ideally these changes would by applied as a post-generation step.
   make generate
   

This runs the OpenAPI Generator Docker image and synchronizes the generated gravatar_api_client/openapi_client into src/openapi_client.

Configuration

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

<details>
<summary>Using uvx</summary>

"mcpServers": {
  "git": {
    "command": "uvx",
    "args": ["--from", "git+https://github.com/andrewdmontgomery/mcp-server-gravatar", "mcp-server-gravatar"]
  }
}

Or if you want to load a specific branch (e.g. add/my-feature):

"mcpServers": {
  "git": {
    "command": "uvx",
    "args": ["--from", "git+https://github.com/andrewdmontgomery/mcp-server-gravatar@add/my-feature", "mcp-server-gravatar"]
  }
}

</details>

Running the MCP Server

You can start the server directly:

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.