feat: initial implementation

.github/workflows/release.yml

@@ -0,0 +1,52 @@
+# https://semantic-release.gitbook.io/semantic-release/recipes/ci-configurations/github-actions
+name: Release
+on:
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: read
+
+jobs:
+  release:
+    name: Release
+
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write
+      issues: write
+      pull-requests: write
+      id-token: write
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 'lts/*'
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v2
+        with:
+          version: 10
+
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Build
+        run: pnpm build
+
+      - name: Verify the integrity of provenance attestations and registry signatures for installed dependencies
+        run: npm audit signatures
+
+      - name: Release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+        run: npx semantic-release

.github/workflows/ci.yml → .github/workflows/test.yml

@@ -1,26 +1,24 @@
-name: CI
+name: Test
 
 on:
-  push:
-    branches: [main]
   pull_request:
-    branches: [main]
+    branches:
+      - main
 
 jobs:
   test:
     runs-on: ubuntu-latest
 
-    strategy:
-      matrix:
-        node-version: [20.x, 22.x]
-
     steps:
-      - uses: actions/checkout@v4
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
-      - name: Use Node.js ${{ matrix.node-version }}
+      - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: ${{ matrix.node-version }}
+          node-version: 'lts/*'
 
       - name: Install pnpm
         uses: pnpm/action-setup@v2
@@ -36,8 +34,8 @@ jobs:
       - name: Check formatting
         run: pnpm format:check
 
-      - name: Run tests
-        run: pnpm test
-
       - name: Build
         run: pnpm build
+
+      - name: Run tests
+        run: pnpm test

.releaserc.yml

@@ -0,0 +1,4 @@
+release:
+  branches:
+    - main
+    - next

LICENSE.md

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Thomas Gambet
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,111 @@
+# Fetch MCP Server
+
+A port of the official [Fetch MCP Server](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch) (python) for Node.js.
+
+## Description
+
+A [Model Context Protocol](https://modelcontextprotocol.io/) server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.
+
+The fetch tool will truncate the response, but by using the `start_index` argument, you can specify where to start the content extraction. This lets models read a webpage in chunks, until they find the information they need.
+
+### Available Tools
+
+- `fetch` - Fetches a URL from the internet and extracts its contents as markdown.
+  - `url` (string, required): URL to fetch
+  - `max_length` (integer, optional): Maximum number of characters to return (default: 5000)
+  - `start_index` (integer, optional): Start content from this character index (default: 0)
+  - `raw` (boolean, optional): Get raw content without markdown conversion (default: false)
+
+### Available Prompts
+
+- `fetch` - Fetch a URL and extract its contents as markdown
+  - `url` (string, required): URL to fetch
+
+## Usage
+
+```json
+"mcpServers": {
+  "fetch": {
+    "command": "npx",
+    "args": ["mcp-fetch-node"]
+  }
+}
+```
+
+```json
+"mcpServers": {
+  "fetch": {
+    "command": "docker",
+    "args": ["run", "-i", "--rm", "tgambet/mcp-fetch-node"]
+  }
+}
+```
+
+### Customization - robots.txt
+
+By default, the server will obey a websites robots.txt file if the request came from the model (via a tool), but not if
+the request was user initiated (via a prompt). This can be disabled by adding the argument `--ignore-robots-txt` to the
+`args` list in the configuration.
+
+### Customization - User-agent
+
+By default, depending on if the request came from the model (via a tool), or was user initiated (via a prompt), the
+server will use either the user-agent
+
+```
+ModelContextProtocol/1.0 (Autonomous; +https://github.com/tgambet/mcp-fetch-node)
+```
+
+or
+
+```
+ModelContextProtocol/1.0 (User-Specified; +https://github.com/tgambet/mcp-fetch-node)
+```
+
+This can be customized by adding the argument `--user-agent=YourUserAgent` to the `args` list in the configuration.
+
+## Features
+
+- [x] Fetch and extract content from a URL
+- [x] Respect `robots.txt` (can be disabled)
+- [x] User-Agent customization
+- [x] Relevant content extraction
+- [x] Raw content or markdown conversion
+- [x] Pagination
+- [ ] In-memory temporary cache for faster responses, especially when paginating
+- [ ] Logs and progress
+
+## Development
+
+```bash
+pnpm install
+pnpm dev
+pnpm lint:fix
+pnpm format
+pnpm test
+pnpm build
+pnpm start
+# test with MCP CLI
+pnpx @wong2/mcp-cli --sse http://localhost:8080/sse
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## License
+
+[MIT](https://choosealicense.com/licenses/mit/)
+
+## TODO
+
+- [ ] Explain key differences with the original mcp/fetch tool
+- [ ] Add LRU cache
+- [ ] Publish to npm
+- [ ] Dockerize and publish to docker hub
+- [ ] Integrate semantic release
+- [ ] Add user logs and progress
+- [ ] Add tests
+- [ ] Add documentation & examples
+- [ ] Add benchmarks for extraction: cf https://github.com/adbar/trafilatura/blob/master/tests/comparison_small.py
+- [ ] Showcase on FastMCP and MCP repositories

eslint.config.js

@@ -0,0 +1,21 @@
+// @ts-check
+
+import eslint from '@eslint/js';
+import tseslint from 'typescript-eslint';
+
+export default tseslint.config(
+  eslint.configs.recommended,
+  tseslint.configs.strictTypeChecked,
+  tseslint.configs.stylisticTypeChecked,
+  {
+    languageOptions: {
+      parserOptions: {
+        projectService: true,
+        tsconfigRootDir: import.meta.dirname,
+      },
+    },
+    rules: {
+      '@typescript-eslint/no-explicit-any': 'off',
+    },
+  },
+);