FetchV2

io.github.praveencPublished by GitHub account praveencv2.0.0Updated Oct 24, 2026

Fetch and extract web pages, discover links, and read llms.txt documentation indexes.

VerifiedSTDIODesktop onlyWeb Search & Scraping Knowledge & Memory

Server details

Identifier: io.github.praveenc/fetchv2-mcp-server
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account praveenc for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.praveenc%2Ffetchv2-mcp-server.svg)](https://sourceweft.com/mcp/io.github.praveenc%2Ffetchv2-mcp-server?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

A local MCP server that fetches web pages, extracts their main content as clean Markdown, discovers links, and reads llms.txt documentation indexes.

What you can do: Fetch one page and extract its main content as Markdown, with options for raw HTML, metadata, tables, links and pagination by character offset. Fetch up to 10 pages in one batch request and combine the results. Discover and regex-filter links on a page, resolving relative URLs. Read an llms.txt index and optionally fetch all its linked pages. Use built-in prompts to fetch and summarize a URL or research a topic.
When to use it: Useful when an assistant needs to read documentation or articles from the web as clean text, gather several pages at once, or work through an llms.txt-based documentation site. Good for research and documentation workflows where raw HTML is too noisy.
Requirements: Runs locally over stdio as a Python package (fetchv2-mcp-server) via uvx or pip. Needs uv and Python 3.11 or newer. No accounts, API keys, environment variables or headers are declared. Network access to the target sites is required.

Before you install

The fetch tool checks robots.txt by default, but the bypass_robots_txt option skips that check, and fetch_batch does not check robots.txt at all. Fetching llms.txt with include_content enabled can return a very large response. Requested pages are retrieved from third-party sites, so their content reaches the assistant.

Installation

In SourceWeft

Open FetchV2 in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

FetchV2 MCP Server

[PyPI version] [CI] [Python 3.11+] [License: MIT]

FetchV2 is a Model Context Protocol (MCP) server that retrieves web pages and returns clean Markdown. It uses Trafilatura to remove navigation, advertisements, footers, and other page elements.

What it does

Tool	Use
`fetch`	Fetch one web page and extract its main content
`fetch_batch`	Fetch up to 10 web pages in one request
`discover_links`	Find and filter links on a web page
`fetch_llms_txt`	Read an llms.txt index and optionally fetch its linked pages

FetchV2 can return raw HTML, preserve links and tables, and paginate long content. The fetch tool checks robots.txt by default.

Quick start

Requirements

Install uv.
Install Python 3.11 or newer:

Install for Cursor or VS Code

Configure another MCP client

Add this server definition to your MCP client configuration:

json

{  "mcpServers": {    "fetchv2": {      "command": "uvx",      "args": ["fetchv2-mcp-server@latest"]    }  }}

{  "mcpServers": {    "fetchv2": {      "command": "uvx",      "args": ["fetchv2-mcp-server@latest"]    }  }}

Common configuration file locations:

Claude Desktop on macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Claude Desktop on Windows: %APPDATA%\Claude\claude_desktop_config.json
Windsurf: ~/.codeium/windsurf/mcp_config.json
Kiro: .kiro/settings/mcp.json in your project

Install in a Python environment

Use one of these commands if you want to install the package directly:

Try it

Ask your MCP client to perform a task such as:

"Fetch the documentation from <URL>."
"Find links on <docs URL> that contain tutorial."
"Read these pages and summarize their differences: [url1, url2, url3]."

Typical documentation workflow

First, find the relevant pages:

Then fetch the selected pages in one request:

python

fetch_batch(    urls=[        "https://docs.example.com/guide/intro",        "https://docs.example.com/guide/setup",    ])

fetch_batch(    urls=[        "https://docs.example.com/guide/intro",        "https://docs.example.com/guide/setup",    ])

Tool reference

`fetch`

Fetch one web page and extract its main content as Markdown.

python

fetch(    url: str,    max_length: int = 5000,    start_index: int = 0,    get_raw_html: bool = False,    include_metadata: bool = True,    include_tables: bool = True,    include_links: bool = False,    bypass_robots_txt: bool = False,) -> str

fetch(    url: str,    max_length: int = 5000,    start_index: int = 0,    get_raw_html: bool = False,    include_metadata: bool = True,    include_tables: bool = True,    include_links: bool = False,    bypass_robots_txt: bool = False,) -> str

Parameter	Type	Default	Description
`url`	`str`	required	Web page URL
`max_length`	`int`	`5000`	Maximum number of characters to return
`start_index`	`int`	`0`	Character offset for pagination
`get_raw_html`	`bool`	`False`	Return raw HTML without extraction
`include_metadata`	`bool`	`True`	Include the title, author, and date
`include_tables`	`bool`	`True`	Preserve tables in Markdown
`include_links`	`bool`	`False`	Preserve links in Markdown
`bypass_robots_txt`	`bool`	`False`	Skip the `robots.txt` check for a user-requested fetch

If the response is truncated, use the returned start_index value in the next call.

`fetch_batch`

Fetch up to 10 web pages and combine the results.

python

fetch_batch(    urls: list[str],    max_length_per_url: int = 2000,    get_raw_html: bool = False,) -> str

fetch_batch(    urls: list[str],    max_length_per_url: int = 2000,    get_raw_html: bool = False,) -> str

Parameter	Type	Default	Description
`urls`	`list[str]`	required	Web page URLs to fetch
`max_length_per_url`	`int`	`2000`	Maximum number of characters to return for each URL
`get_raw_html`	`bool`	`False`	Return raw HTML without extraction

This tool reports a failed URL in its result and continues with the other URLs. It does not check robots.txt.

`discover_links`

Find links on a web page and optionally filter them with a regular expression.

The tool resolves relative links and returns up to 100 URLs.

`fetch_llms_txt`

Read an llms.txt file and list its documentation links.

python

fetch_llms_txt(    url: str,    include_content: bool = False,    max_length_per_url: int = 2000,) -> str

fetch_llms_txt(    url: str,    include_content: bool = False,    max_length_per_url: int = 2000,) -> str

Parameter	Type	Default	Description
`url`	`str`	required	URL of an `llms.txt` file
`include_content`	`bool`	`False`	Fetch the content of all linked pages
`max_length_per_url`	`int`	`2000`	Maximum number of characters to return for each linked page

By default, this tool fetches only the llms.txt index. Set include_content=True to fetch all linked pages. This option can return a large response.

The tool resolves relative URLs, such as /docs/guide.md, against the llms.txt URL.

Prompts

fetch_manual creates a request to fetch and summarize one URL.
research_topic creates a request to research a topic with optional URLs.

Development

Clone the repository and install the development dependencies:

Run the tests:

Run the server with MCP Inspector:

Run lint and type checks:

Contributing

Read CONTRIBUTING.md before you submit a change.

Support

Use the GitHub issue tracker to report a problem or request a feature.

License

This project uses the MIT License. See LICENSE for details.

Source: README.md at commit b6a920d

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v2.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts