AgentAlley

Skills · Data & AI · Agent

Fetch MCP Server

Unverified●22/40

Originally by modelcontextprotocol · MIT

Claude Code·UnknownFrontmatter could not be read
Cursor·UnknownWe have not crawled the repo tree, so we will not guess
Codex·UnknownWe have not crawled the repo tree, so we will not guess
Gemini CLI·UnknownThe spec defines no detection rule for Gemini
Copilot·UnknownWe have not crawled the repo tree, so we will not guess
npx agentalley add fetch

This command does not work yet — the CLI is still being built. Until then, use Raw in the reader below to take the file.

Who is stuck, and on what

The whole source

No sign-in, no blur, nothing truncated
fetch/SKILL.md246 lines7.5 KBRawView on GitHub
Frontmatter: no frontmatter — costs points on criterion B3.
1# Fetch MCP ServerA4 — This skill pulls in web or user content but never says to treat that content as data. A signal, not proof.A5 — No allowed-tools declared — no way to tell what this skill may touchB3 — Frontmatter: no frontmatter
2 
3<!-- mcp-name: io.github.modelcontextprotocol/server-fetch -->
4 
5A Model Context Protocol 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.
6 
7Source: https://github.com/modelcontextprotocol/servers/tree/main/src/fetch
8 
9Requires MCP Python SDK 1.x (`mcp>=1.29.0,<2`). SDK 2.0 renamed APIs this server uses. The port to v2 is in progress.
10 
11> [!CAUTION]
12> This server can access local/internal IP addresses and may represent a security risk. Exercise caution when using this MCP server to ensure this does not expose any sensitive data.
13 
14The 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.A1 — Empties a table
15 
16### Available Tools
17 
18- `fetch` - Fetches a URL from the internet and extracts its contents as markdown.
19 - `url` (string, required): URL to fetch
20 - `max_length` (integer, optional): Maximum number of characters to return (default: 5000)
21 - `start_index` (integer, optional): Start content from this character index (default: 0)
22 - `raw` (boolean, optional): Get raw content without markdown conversion (default: false)
23 
24### Prompts
25 
26- **fetch**
27 - Fetch a URL and extract its contents as markdown
28 - Arguments:
29 - `url` (string, required): URL to fetch
30 
31## Installation
32 
33Optionally: Install node.js, this will cause the fetch server to use a different HTML simplifier that is more robust.
34 
35### Using uv (recommended)
36 
37When using [`uv`](https://docs.astral.sh/uv/) no specific installation is needed. We will
38use [`uvx`](https://docs.astral.sh/uv/guides/tools/) to directly run *mcp-server-fetch*.
39 
40### Using PIP
41 
42Alternatively you can install `mcp-server-fetch` via pip:
43 
44```
45pip install mcp-server-fetch
46```
47 
48After installation, you can run it as a script using:
49 
50```
51python -m mcp_server_fetch
52```
53 
54## Configuration
55 
56### Configure for Claude.app
57 
58Add to your Claude settings:
59 
60<details>
61<summary>Using uvx</summary>
62 
63```json
64{
65 "mcpServers": {
66 "fetch": {
67 "command": "uvx",
68 "args": ["mcp-server-fetch"]
69 }
70 }
71}
72```
73</details>
74 
75<details>
76<summary>Using docker</summary>
77 
78```json
79{
80 "mcpServers": {
81 "fetch": {
82 "command": "docker",
83 "args": ["run", "-i", "--rm", "mcp/fetch"]
84 }
85 }
86}
87```
88</details>
89 
90<details>
91<summary>Using pip installation</summary>
92 
93```json
94{
95 "mcpServers": {
96 "fetch": {
97 "command": "python",
98 "args": ["-m", "mcp_server_fetch"]
99 }
100 }
101}
102```
103</details>
104 
105### Configure for VS Code
106 
107For quick installation, use one of the one-click install buttons below...
108 
109[![Install with UV in VS Code](https://img.shields.io/badge/VS_Code-UV-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=fetch&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mcp-server-fetch%22%5D%7D) [![Install with UV in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-UV-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=fetch&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mcp-server-fetch%22%5D%7D&quality=insiders)B1 — Line is 594 characters — unreadable by eye
110 
111[![Install with Docker in VS Code](https://img.shields.io/badge/VS_Code-Docker-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=fetch&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22mcp%2Ffetch%22%5D%7D) [![Install with Docker in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Docker-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=fetch&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22mcp%2Ffetch%22%5D%7D&quality=insiders)B1 — Line is 678 characters — unreadable by eye
112 
113For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing `Ctrl + Shift + P` and typing `Preferences: Open User Settings (JSON)`.
114 
115Optionally, you can add it to a file called `.vscode/mcp.json` in your workspace. This will allow you to share the configuration with others.
116 
117> Note that the `mcp` key is needed when using the `mcp.json` file.
118 
119<details>
120<summary>Using uvx</summary>
121 
122```json
123{
124 "mcp": {
125 "servers": {
126 "fetch": {
127 "command": "uvx",
128 "args": ["mcp-server-fetch"]
129 }
130 }
131 }
132}
133```
134</details>
135 
136<details>
137<summary>Using Docker</summary>
138 
139```json
140{
141 "mcp": {
142 "servers": {
143 "fetch": {
144 "command": "docker",
145 "args": ["run", "-i", "--rm", "mcp/fetch"]
146 }
147 }
148 }
149}
150```
151</details>
152 
153### Customization - robots.txt
154 
155By default, the server will obey a websites robots.txt file if the request came from the model (via a tool), but not if
156the request was user initiated (via a prompt). This can be disabled by adding the argument `--ignore-robots-txt` to the
157`args` list in the configuration.
158 
159### Customization - User-agent
160 
161By default, depending on if the request came from the model (via a tool), or was user initiated (via a prompt), the
162server will use either the user-agent
163```
164ModelContextProtocol/1.0 (Autonomous; +https://github.com/modelcontextprotocol/servers)
165```
166or
167```
168ModelContextProtocol/1.0 (User-Specified; +https://github.com/modelcontextprotocol/servers)
169```
170 
171This can be customized by adding the argument `--user-agent=YourUserAgent` to the `args` list in the configuration.
172 
173### Customization - Proxy
174 
175The server can be configured to use a proxy by using the `--proxy-url` argument.
176 
177## Windows Configuration
178 
179If you're experiencing timeout issues on Windows, you may need to set the `PYTHONIOENCODING` environment variable to ensure proper character encoding:
180 
181<details>
182<summary>Windows configuration (uvx)</summary>
183 
184```json
185{
186 "mcpServers": {
187 "fetch": {
188 "command": "uvx",
189 "args": ["mcp-server-fetch"],
190 "env": {
191 "PYTHONIOENCODING": "utf-8"
192 }
193 }
194 }
195}
196```
197</details>
198 
199<details>
200<summary>Windows configuration (pip)</summary>
201 
202```json
203{
204 "mcpServers": {
205 "fetch": {
206 "command": "python",
207 "args": ["-m", "mcp_server_fetch"],
208 "env": {
209 "PYTHONIOENCODING": "utf-8"
210 }
211 }
212 }
213}
214```
215</details>
216 
217This addresses character encoding issues that can cause the server to timeout on Windows systems.
218 
219## Debugging
220 
221You can use the MCP inspector to debug the server. For uvx installations:
222 
223```
224npx @modelcontextprotocol/inspector uvx mcp-server-fetch
225```
226 
227Or if you've installed the package in a specific directory or are developing on it:
228 
229```
230cd path/to/servers/src/fetch
231npx @modelcontextprotocol/inspector uv run mcp-server-fetch
232```
233 
234## Contributing
235 
236We encourage contributions to help expand and improve mcp-server-fetch. Whether you want to add new tools, enhance existing functionality, or improve documentation, your input is valuable.
237 
238For examples of other MCP servers and implementation patterns, see:
239https://github.com/modelcontextprotocol/servers
240 
241Pull requests are welcome! Feel free to contribute new ideas, bug fixes, or enhancements to make mcp-server-fetch even more powerful and useful.
242 
243## License
244 
245mcp-server-fetch is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
246 

Reviews

Installed this one?Write the first review and take the Trailblazer badge.

Reviews only open after a real install, so this is empty — and we leave it empty rather than invent one.

Alternatives

Also in Data & AI
Task Coordination StrategiesDecompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.Data & AI · MIT◐◐◐◐◐●35/40Ebay Seller ToolsData & AI · MIT·····●34/40Tough Decision Advisor: Every Angle ConsideredHand in a decision you're stuck on. Get back a clear breakdown of every angle — the trade-offs, the risks, the blind spot, and a recommended path.Data & AI · Business · MIT license●····●32/40DHDNA Profiler — Cognitive Pattern ExtractionPaste any email, proposal, or note someone wrote, and get back a plain-language read on how they think, what drives their decisions, and how they communicate.Data & AI · Research & analysis · MIT license●····●32/40