Fetch MCP Server

What does “Fetch” MCP Server do?

The Fetch MCP Server is a flexible Model Context Protocol (MCP) server designed to fetch web content in various formats, including HTML, JSON, plain text, and Markdown. By acting as a bridge between AI assistants and external web resources, Fetch MCP enables AI-driven applications to retrieve and transform web data on demand. This empowers developers and AI agents to incorporate dynamic web content into their workflows, whether it’s for data extraction, content summarization, or further processing. The server supports custom request headers, leverages modern fetch APIs, and includes tools for parsing and converting web data, making it a valuable asset for tasks that require real-time access to online information.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

• The Fetch MCP Server does not provide any persistent resources. It is designed to fetch and transform web content on demand.

List of Tools

• fetch_html
  Fetch a website and return the content as HTML.
  Input: url (required), headers (optional).
  Output: Raw HTML content of the webpage.

• fetch_json
  Fetch a JSON file from a URL.
  Input: url (required), headers (optional).
  Output: Parsed JSON content.

• fetch_txt
  Fetch a website and return the content as plain text (no HTML).
  Input: url (required), headers (optional).
  Output: Plain text with HTML tags, scripts, and styles removed.

• fetch_markdown
  Fetch a website and return the content as Markdown.
  Input: url (required), headers (optional).
  Output: Webpage content converted to Markdown format.

Use Cases of this MCP Server

• Web Content Extraction
  Retrieve the HTML, JSON, or plain text from public websites for further analysis or summarization by AI agents.

• Content Transformation
  Convert website content into Markdown or plain text formats for easier consumption or integration into note-taking and documentation tools.

• API Data Retrieval
  Fetch structured data from public APIs (in JSON format) for use in workflows, dashboards, or as context for LLM-driven applications.

• Custom Data Gathering
  Supply custom headers to access content from endpoints requiring specific authentication or headers, enabling more advanced data retrieval scenarios.

• Content Parsing for AI Agents
  Equip AI assistants with the ability to parse and utilize live web content during conversations, research, or automation tasks.

How to set it up

Windsurf

1. Ensure Node.js is installed on your system.
2. Clone the Fetch MCP repository and install dependencies (npm install).
3. Build the server with npm run build.
4. Add the following to your Windsurf configuration file:

   {
     "mcpServers": {
       "fetch": {
         "command": "node",
         "args": [
           "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
         ]
       }
     }
   }
   

5. Restart Windsurf and verify the MCP server is running.

Securing API Keys

Insert environment variables as needed:

{
  "mcpServers": {
    "fetch": {
      "command": "node",
      "args": ["{ABSOLUTE PATH TO FILE HERE}/dist/index.js"],
      "env": {
        "API_KEY": "${FETCH_API_KEY}"
      },
      "inputs": {
        "api_key": "${FETCH_API_KEY}"
      }
    }
  }
}

Claude

1. Ensure Node.js is installed.
2. Follow repository setup steps (clone, install, build).
3. Edit the Claude MCP configuration:

   {
     "mcpServers": {
       "fetch": {
         "command": "node",
         "args": [
           "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
         ]
       }
     }
   }
   

4. Save the file and restart Claude.
5. Confirm the Fetch MCP Server is available.

Securing API Keys

See the Windsurf section for the JSON example.

Cursor

1. Install Node.js.
2. Clone and build the Fetch MCP Server (npm install, npm run build).
3. Add to Cursor’s MCP configuration:

   {
     "mcpServers": {
       "fetch": {
         "command": "node",
         "args": [
           "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
         ]
       }
     }
   }
   

4. Save and restart Cursor.
5. Validate successful connection.

Securing API Keys

Use the same JSON format as above for environment variables.

Cline

1. Ensure Node.js is installed.
2. Clone and build the Fetch MCP Server.
3. Configure Cline MCP with:

   {
     "mcpServers": {
       "fetch": {
         "command": "node",
         "args": [
           "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
         ]
       }
     }
   }
   

4. Restart Cline and verify the server is working.

Securing API Keys

Follow the previous environment variable JSON example.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "fetch": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “fetch” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

I would rate the Fetch MCP Server as a solid 7/10. It is practical, has clear documentation, a proper license, and multiple useful tools, but lacks prompt templates, persistent resources, and information on roots or sampling support.

MCP Score