MCP time (reference)
Time and timezone conversion
CCCXGBCUPi
SkillMaxx / Utilities / MCP fetch (reference)
MCP fetch (reference)
Web content fetching and conversion for LLM use
- Stars
- ★ 91k
- Last updated
- Hands-on tests
- Tested ✓ in 2 of 5
Install
Tested ✓✓ Verified from docsOfficial docs ↗
claude mcp add fetch -- uvx mcp-server-fetchTested ✓ on 2026-10-16: installed and loaded in a throwaway sandbox with no credentials.
Log excerpt
Added stdio MCP server mcpfetch with command: uvx mcp-server-fetch to local config File modified: /home/sbx/.claude.json [project: /home/sbx] $ verify: mcpfetch: uvx mcp-server-fetch - ✔ Connected
1 run, latest 2026-10-16
✓ Verified from docsOfficial docs ↗
codex mcp add fetch -- uvx mcp-server-fetchChecked against official docs on 2026-10-16. Hands-on test not available for this agent yet.
Not yet tested
No official Grok Build instructions yet. We haven't found docs saying this works in Grok Build.
Know it works? Tell us →Tested ✓✓ Verified from docsOfficial docs ↗
~/.cursor/mcp.json: {"mcpServers":{"fetch":{"command":"uvx","args":["mcp-server-fetch"]}}}Tested ✓ on 2026-10-16: installed and loaded in a throwaway sandbox with no credentials.
Log excerpt
✓ Enabled and approved MCP server: mcpfetch $ verify: mcpfetch: ready Tools for mcpfetch (1):
1 run, latest 2026-10-16
Not yet tested
No official Pi instructions yet. We haven't found docs saying this works in Pi.
Know it works? Tell us →README
View on GitHub ↗Fetch MCP Server
A 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.
Source: https://github.com/modelcontextprotocol/servers/tree/main/src/fetch
Requires 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.
[!CAUTION] 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.
By default the server refuses to fetch private, loopback, link-local and other non-public addresses, including cloud metadata endpoints such as
169.254.169.254, and checks every redirect hop the same way. The--allow-private-ipsargument turns this guard off; see Customization - Private addresses. The guard checks the addresses a hostname resolves to before each request, so it does not protect against DNS rebinding between that check and the connection, and a hostname the server cannot resolve itself (one only a proxy can resolve) is not checked.
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 fetchmax_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)- Annotations:
readOnlyHint: true,destructiveHint: false,idempotentHint: true,openWorldHint: true(it only reads, and it reaches arbitrary hosts on the internet)
Prompts
- fetch
- Fetch a URL and extract its contents as markdown
- Arguments:
url(string, required): URL to fetch
Installation
Optionally: Install node.js, this will cause the fetch server to use a different HTML simplifier that is more robust.
Preview from the source repo. Images are removed.
