Fetch MCP Server for VS Code: Setup & Config

What you can do with Fetch in VS Code

Choose format-specific web retrieval with readable articles, transcripts, and bounded output.

• Bring a web article into an assistant as cleaned Markdown.
• Read long pages in character-based chunks.

Before you start: Fetch in VS Code

• Node.js with npx
• Optional yt-dlp for transcript extraction

This is the README MCP launch, not the mcp-fetch CLI invocation. The supplied structured tool catalog and README list different tools; verify the running server tool list.

Fetch VS Code configuration

1. Choose VS Code configuration scope

   For Fetch MCP Server, open Workspace: .vscode/mcp.json. Merge into servers; preserve existing inputs.

2. Add Fetch MCP Server to VS Code

   Use the fetch-mcp-zcaceres entry below in servers. Keep Fetch MCP Server's documented stdio connection fields and your other VS Code entries.

3. Check Fetch MCP Server in VS Code

   Fetch MCP Server: Start in VS Code’s MCP controls; inspect output and trust prompts.

{
  "servers": {
    "fetch-mcp-zcaceres": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "mcp-fetch-server"
      ],
      "env": {
        "DEFAULT_LIMIT": "<Optional default response character limit>",
        "MAX_RESPONSE_BYTES": "<Optional response-body byte limit>"
      }
    }
  }
}

Fetch tools available to VS Code

Fetch's stored tool list documents 11 tools; compare it with VS Code's connected tool list, because the stored list is not a live check.

fetch_html

Look for fetch_html among VS Code's agent-mode tools after starting Fetch through the MCP controls.

fetch_markdown

Look for fetch_markdown among VS Code's agent-mode tools after starting Fetch through the MCP controls.

Convert fetched page content to Markdown.

fetch_txt

Look for fetch_txt among VS Code's agent-mode tools after starting Fetch through the MCP controls.

Return page text without HTML tags, scripts, or styles.

fetch_json

Look for fetch_json among VS Code's agent-mode tools after starting Fetch through the MCP controls.

Retrieve a URL returning JSON.

fetch_readable

Look for fetch_readable among VS Code's agent-mode tools after starting Fetch through the MCP controls.

fetch_youtube_transcript

Look for fetch_youtube_transcript among VS Code's agent-mode tools after starting Fetch through the MCP controls.

fetch

Look for fetch among VS Code's agent-mode tools after starting Fetch through the MCP controls.

Issue an HTTP request with configurable method, headers, body, and options.

get-rules

Look for get-rules among VS Code's agent-mode tools after starting Fetch through the MCP controls.

Retrieve guidance on using the server tools.

graphql

Look for graphql among VS Code's agent-mode tools after starting Fetch through the MCP controls.

Run GraphQL queries or mutations with variables and headers.

puppeteer

Look for puppeteer among VS Code's agent-mode tools after starting Fetch through the MCP controls.

socket

Look for socket among VS Code's agent-mode tools after starting Fetch through the MCP controls.

Fetch: full stored tool descriptions

Troubleshooting Fetch in VS Code

• Make npx mcp-fetch-server (Node.js/npm) available in the workspace, container, or remote environment hosting Fetch MCP Server. Start through VS Code's MCP controls; inspect output and trust prompts.
• For Fetch MCP Server, keep DEFAULT_LIMIT, MAX_RESPONSE_BYTES out of version control; VS Code documents input variables and secret handling.
• Fetch MCP Server uses stdio here: VS Code must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
• Known limitation: Default response character and byte limits constrain large fetches.
• Known limitation: Structured input tools differ from the README tool list.
• Known limitation: Private and localhost targets are blocked by the documented SSRF protection.
• General VS Code troubleshooting lives in the /clients/vscode guide.

Frequently asked questions