Make Your

Provides an MCP server that exposes a curl-based webpage fetch tool for LLM-assisted content retrieval.

go

8

GitHub Stars

go

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ollama-tlms-golang-05-make-your-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "mcp-curl"
      ]
    }
  }
}

You can build a minimal MCP server in Go that exposes a single tool which fetches a webpage using curl, and run it inside Docker for easy deployment. This pattern demonstrates how an LLM can call an external tool to retrieve web content and return it as plain text.

How to use

You will run a small MCP server that provides one tool named use_curl. Your client can request a URL to fetch, and the server will execute curl on that URL and return the page content as text. With Docker, you can start the server container and then connect from an MCP client or host tool to request the tool and its results. You can also use a local host configurator to expose and manage the server from a central workflow.

How to install

Prerequisites you need before starting:

Docker installed on your system.

Steps to build and run the MCP server locally:

# Build the MCP server image from a simple Go project used in this pattern
# The server code is prepared to expose a single curl-fetching tool
# Build the Docker image for the MCP server

docker build -t mcp-curl .

Additional content

Configure and run the MCP server via Docker, then connect it to an MCP client setup to manage tools and execute requests.

# Example MCP configuration for an MCP host to talk to the Docker-based MCP server
# This uses a docker run command to start the server container and connect via stdio
{
  "mcpServers": {
    "mcp-curl-with-docker": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "mcp-curl"
      ]
    }
  }
}

Using mcphost to interact with the server

Once you have the MCP server available, you can work with mcphost to start an LLM-assisted workflow that uses the server to fetch pages.

mcphost --config ./mcp.json --model ollama:qwen2.5-coder:14b

Notes on the server and tool

The server exposes a single tool named use_curl which accepts a required url parameter. The handler executes curl -s <url> and returns the page content as text. Errors are reported back to the caller as tool results.

Available tools

use_curl

Fetch a webpage by URL. The tool requires a single string parameter named url and returns the page content as text.