Hippycampus (OpenAPI Tools) MCP server

Hippycampus is a LangChain-based tool that provides both a CLI and Model Context Protocol (MCP) server. It allows for dynamic loading of OpenAPI specifications and seamless integration with Langflow for visual workflow creation, making it easier to work with various AI models and APIs.

Prerequisites

• Python 3.12.9
• UV package manager
• Google AI Studio API key
• Langflow (for visual workflow creation)

Installation

First, install the UV package manager and set up your environment:

# Install UV if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Create and activate virtual environment
uv venv
source .venv/bin/activate  # On Windows use: .venv\Scripts\activate

# Install hippycampus and its dependencies
uv pip install -e .

# Install langflow
uv pip install langflow

Configuration

Setting Up Google AI Studio API Key

To use Hippycampus, you'll need a Google AI Studio API key:

1. Visit Google AI Studio
2. Click "Create API Key" in the top right
3. Copy the generated key and set it as an environment variable:

export GOOGLE_API_KEY='your-api-key-here'

Using Hippycampus

CLI Mode

To run Hippycampus in CLI mode (without the MCP server):

uv run hippycampus-cli

MCP Server Mode

To start the MCP server using Server-Sent Events (SSE) transport:

uv run hippycampus-server --transport sse --port 8000

Running with Langflow

For visual workflow creation, you can use Hippycampus with Langflow:

1. Set the components path environment variable:

# Get your current working directory
pwd
# Use the output to set the components path
export LANGFLOW_COMPONENTS_PATH="/output/from/pwd/langflow/components"

2. Start the Langflow server:

uv run langflow run

3. Open your browser and navigate to http://localhost:7860

Using Custom Components in Langflow

After starting both the MCP server and Langflow:

1. In the Langflow UI, locate the custom components:

   • OpenApi Service: For loading OpenAPI specifications
   • Hippycampus MCP Server: For connecting to the MCP server over SSE

2. Configure the components:

   • For OpenApi Service, you can use https://raw.githubusercontent.com/APIs-guru/unofficial_openapi_specs/master/xkcd.com/1.0.0/openapi.yaml as a test
   • For MCP Server, use http://localhost:8000/sse

A visual guide is available in the Screencast Demo.

Troubleshooting

If you encounter issues:

• Authentication errors: Ensure your GOOGLE_API_KEY is set correctly
• Missing components in Langflow: Verify LANGFLOW_COMPONENTS_PATH points to the correct directory
• Connection issues: Make sure the MCP server is running before connecting via Langflow
• Components not appearing in Langflow: Try restarting the Langflow server
• Integration issues: Use the CLI to debug openapi_builder/spec_parser and agent interactions before using MCP/Langflow

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "hippycampus-server" '{"command":"uv","args":["run","hippycampus-server","--transport","sse","--port","8000"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "hippycampus-server": {
            "command": "uv",
            "args": [
                "run",
                "hippycampus-server",
                "--transport",
                "sse",
                "--port",
                "8000"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "hippycampus-server": {
            "command": "uv",
            "args": [
                "run",
                "hippycampus-server",
                "--transport",
                "sse",
                "--port",
                "8000"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect