Fetch V2 MCP Server

FetchV2 is a Model Context Protocol (MCP) server that retrieves web pages and returns clean Markdown. Its 3 documented tools cluster into read & search, discover. It runs locally over stdio via the published package.

People who work with content extraction, markdown and web fetching and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-08 · ★ 3 · #55 OF 93 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Fetch V2

Claude Code

claude mcp add praveenc-fetchv2-mcp-server -- uvx fetchv2-mcp-server

Claude Desktop / Cursor / VS Code - add to config

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

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package fetchv2-mcp-server - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.praveenc is GitHub-verified and matches the repo owner

03 · What Fetch V2 can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can fetch up to 10 web pages and combine the results, find links on a web page and optionally filter them with a regular expression, and read an llms.txt file and list its documentation links.

The 3 tools it gives your agent

Extracted from the project's README - what FetchV2 lets an agent do.

fetch_batch
- Fetch up to 10 web pages and combine the results.
discover_links
- Find links on a web page and optionally filter them with a regular expression.
fetch_llms_txt
- Read an llms.txt file and list its documentation links.

Latest releases

v2.0.0 · 2026-09-08

Migrate to MCP SDK v2 · Automate PyPI and MCP Registry release · New Contributors · @praveenc made their first contribution in

v1.1.0 · 2025-12-06

Added · fetch_llms_txt tool - Parse and fetch LLM-friendly documentation from llms.txt files · Support for the llms.txt specification · include_content parameter to explicitly fetch all linked pages in one request…

v1.0.1 · 2025-12-05

Changed · Improved README with one-click install buttons for Cursor and VS Code · Added Prerequisites section with uv/Python requirements · Added Basic Usage section with example prompts · Converted tool parameters to…

04 · Who maintains Fetch V2

FetchV2 is maintained by praveenc. We track 3 MCP servers from praveenc - 3 actively maintained, 5 combined GitHub stars, oldest repo from Dec 2025.

05 · Facts

category
web scraping - ranked #55 of 93 actively-maintained web scraping servers as of 2026-09-18.
release cadence
1 release in the last 90 days (latest 2026-09-08)
registry
io.github.praveenc/fetchv2-mcp-server (active, first published 2026-09-08)
packages
pypi:fetchv2-mcp-server

06 · Fetch V2 FAQ

Is Fetch V2 still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-08 and it shipped 1 release in the last 90 days. We re-verify nightly.

What can Fetch V2 do?

With this server connected, an agent can fetch up to 10 web pages and combine the results, find links on a web page and optionally filter them with a regular expression, and read an llms.txt file and list its documentation links.

How do I install Fetch V2?

Run `uvx fetchv2-mcp-server`. You can also paste the ready-made client config above.

Does Fetch V2 run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Fetch V2

More web scraping MCP servers · Crawlgraph MCP · Pulse Fetch · Fitter · Doc Pull · Rampify

More Python MCP servers · reMarkable MCP Server (Read/Write) · Précis Finance MCP · Dbt Plan · Presidio Hardened X402 MCP · Kairn · see all