About Beehiiv MCP Server
A Python MCP server that connects LLMs to Beehiiv API v2 publication and post operations. It provides tools for listing publications and posts, retrieving post details and content, and creating posts.
Key features
- 01List accessible publications
- 02List recent confirmed posts
- 03Retrieve post details
- 04Retrieve full HTML content
- 05Create posts for enterprise accounts
Use cases
- 01Inspecting Beehiiv publications
- 02Reviewing recent posts
- 03Retrieving post details or HTML
- 04Creating enterprise posts
MCP support
The server exposes Beehiiv API v2 operations as tools to MCP clients, including publication and post retrieval and post creation.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEBeehiiv MCP Server
A Model Context Protocol (MCP) server that provides tools for interacting with the Beehiiv API v2. This server enables Large Language Models (LLMs) to interact with Beehiiv publications and posts through standardized tools.
Prerequisites
- Python 3.10 or higher
uvpackage manager- A Beehiiv account with API access
- Claude Desktop (or another MCP-compatible client)
Installation
- Install
uvif you haven't already:
curl -LsSf https://astral.sh/uv/install.sh | sh
- If rebuilding from scratch, create and set up your project:
# Create a new directory and navigate into it
mkdir beehiiv-mcp-server
cd beehiiv-mcp-server
# Create virtual environment and activate it
uv venv
source .venv/bin/activate
# Install dependencies
uv add "mcp[cli]" httpx python-dotenv
- Create a
.envfile in the project root:
BEEHIIV_API_KEY=your_api_key_here
BEEHIIV_PUBLICATION_ID=your_publication_id_here
Claude Desktop Configuration
Add the following to your Claude Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"beehiiv-mcp-server": {
"command": "<ABSOLUTE_UV_PATH>",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"<ABSOLUTE_SERVER_PATH>"
]
}
}
}
Replace:
<ABSOLUTE_UV_PATH>with the path to youruvexecutable<ABSOLUTE_SERVER_PATH>with the absolute path to yourbeehiiv_server.pyfile
Available Tools
This MCP server currently exposes the following tools (more will be added):
list_publications
Lists all publications accessible with your API key.
list_posts
Lists the 5 most recent confirmed posts for a given publication.
list_posts(publication_id: str)
get_post
Retrieves detailed information about a specific post.
get_post(publication_id: str, post_id: str)
get_post_content
Retrieves full HTML content for a post
create_new_post
Creates new post on beehiiv platform (enterprise only)
How It Works
When you interact with this server through Claude Desktop:
- The client sends your question to Claude
- Claude analyzes the available Beehiiv tools and decides which one(s) to use
- The client executes the chosen tool(s) through this MCP server
- The results are sent back to Claude
- Claude formulates a natural language response
- The response is displayed to you
(video coming soon)
Troubleshooting
Server Not Showing Up in Claude
- Check your
claude_desktop_config.jsonfile syntax - Ensure all paths are absolute, not relative
- Restart Claude Desktop
Viewing Logs
Check Claude's logs for MCP-related issues:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
Logs are stored in:
~/Library/Logs/Claude/mcp.logfor general MCP connections~/Library/Logs/Claude/mcp-server-beehiiv-mcp-server.logfor server-specific logs
Security
- Never commit your
.envfile to version control - Keep your Beehiiv API key secure
- Consider implementing rate limiting for API calls
Contributing
hmu on X (https://x.com/reymerekar7)
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.