Dictionary & Thesaurus MCP server

The Words MCP Server provides dictionary and thesaurus tools for language models and AI assistants through the Free Dictionary API. It offers utilities like word definitions, example usage sentences, and synonyms that can be called programmatically via FastMCP.

Features

• define – Retrieve definitions of English words
• example_usage – Get example usage sentences for words
• synonyms – Find synonyms for words

Installation Options

Using Python Package

You can install the Words MCP Server using Python package tools:

# Using pip
pip install casual-mcp-server-words

# Using uvx
uvx casual-mcp-server-words

Docker Installation

Build the Docker image from the repository:

docker build -f servers/words/Dockerfile -t casual-mcp-server-words .

Running the Server

The Words MCP Server can run in two modes: Stdio Mode and Streamable HTTP Mode.

Stdio Mode

From Source

After installing for local development:

uv tool run casual-mcp-server-words

Configure in your application:

{
  "mcpServers": {
    "words": {
      "command": "uv",
      "args": ["tool", "run", "casual-mcp-server-words"]
    }
  }
}

Using uvx

Configure:

{
  "mcpServers": {
    "words": {
      "command": "uvx",
      "args": ["casual-mcp-server-words"]
    }
  }
}

Using Docker

Configure:

{
  "mcpServers": {
    "words": {
      "command": "docker",
      "args": ["run", "--rm", "casual-mcp-server-words"]
    }
  }
}

Streamable HTTP Mode

From Source

Run the server with streamable HTTP transport:

uv run casual-mcp-server-words --transport streamable-http

To specify port and host:

uv run casual-mcp-server-words --transport streamable-http --port 9000 --host 0.0.0.0

Using uvx

uvx casual-mcp-server-words --transport streamable-http

Using Docker

docker run -e MCP_TRANSPORT=streamable-http -e MCP_PORT=9000 -p 9000:9000 casual-mcp-server-words

HTTP Mode Configuration

Configure in your application:

{
  "mcpServers": {
    "words": {
      "type": "streamable-http",
      "url": "http://localhost:9000"
    }
  }
}

Using the Tools

Once the server is running, you can use the provided tools in your application:

Define a Word

# Example of using the define tool
result = await mcp.tools.words.define(word="ubiquitous")
print(result)

Get Example Usage

# Example of using the example_usage tool
examples = await mcp.tools.words.example_usage(word="serendipity")
print(examples)

Find Synonyms

# Example of using the synonyms tool
synonyms = await mcp.tools.words.synonyms(word="happy")
print(synonyms)

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.