Fetch MCP in Claude Code

Quick answer: Install the Fetch MCP server with npx -y @modelcontextprotocol/server-fetch, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on @modelcontextprotocol/server-fetch as of April 15, 2026.

The Fetch MCP server gives Claude Code a simple HTTP fetch tool that returns the page content as clean markdown. Where Brave Search lists links, Fetch actually pulls the page and hands Claude the body. Pairing the two turns Claude into a capable research agent that can search, read, and summarize without you manually copying anything.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Fetch server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Fetch day to day, this replaces dozens of context switches per week with a single line in chat.

The server exposes a single tool: fetch. Input is a URL plus optional max_length, start_index, and raw flag. Output is markdown extracted from the HTML using a readability pass, which strips navigation, sidebars, and ads. For structured data (JSON APIs), pass raw=true and Claude gets the body untouched.

Prerequisites

Node 20 or later. No account or API key. Outbound HTTPS must be reachable from your machine, which rules out some corporate networks without a proxy configured.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y @modelcontextprotocol/server-fetch

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-fetch"]
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• Fetch the Next.js 16 release notes at https://nextjs.org/blog/next-16 and summarize the changes in three bullets.
• Pull the latest content from our status page at status.example.com and tell me whether any incidents are open.
• Read the raw JSON at https://api.github.com/repos/anthropics/claude-code and show me the star count plus default branch.
• Fetch this stack overflow thread and extract the top accepted answer with its code block.
• Grab the OpenAPI spec at https://api.example.com/openapi.json, count the endpoints, and list the five most used ones.
• Download the plain text README from a raw GitHub URL and give me a 200-word summary.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

No environment variables are needed for basic use. Behind a corporate proxy, set HTTP_PROXY and HTTPS_PROXY in the shell that launches Claude Code, and the fetch server will honor them. For sites that require a user agent, the server sends a default UA you can override with FETCH_USER_AGENT.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Fetch returns 403 on some sites. The site blocks the default user agent. Set FETCH_USER_AGENT to a common browser UA string, restart Claude Code, and retry.

Pages with heavy JavaScript return empty content. Fetch does not execute JavaScript. For SPA sites that render client-side, use mcp-server-puppeteer instead and have Claude ask that server for the rendered HTML.

Large pages truncate. The server caps the returned markdown at around 50 KB by default. Ask Claude to pass max_length or a start_index to paginate through a large document.

Fetch hangs and never returns. The default timeout is 30 seconds. Some sites hold connections open without sending data. Retry the prompt, and if it keeps failing, verify from curl that the URL returns something useful at all.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Fetch server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.