content-extraction MCP servers

11 tagged content-extraction, measured the same way as everything else here.

firecrawl/firecrawl-mcp-server

MCP server Claude CodeCodexCursor +2

Lets the agent scrape, crawl and search the web through Firecrawl, returning clean markdown. Runs locally from the firecrawl-mcp npm package. Needs 1 environment variable to run.

not rated 7.6k +41 today A Socket: warn tokens not measured original MIT

pinkpixel-dev/web-scout-mcp

MCP server Claude CodeCodexCursor +2

Search the web and extract clean, readable text from webpages. Process multiple URLs at once to sp… Remote server at server.smithery.ai.

not rated 137 +1 20d ago A tokens not measured original Apache-2.0

argus

03

Khamel83/argus

MCP server Claude CodeCodexCursor +2

Retrieval platform for AI agents — 14 search providers, 12-step content extraction, dead URL recovery, site capture, and local corpus storage. One API. Runs locally from the argus-search Python package. Needs 8 environment variables to run.

not rated 5 yesterday A tokens not measured original MIT

fetchv2-mcp-server

04

praveenc/fetchv2-mcp-server

MCP server Claude CodeCodexCursor +2

A robust MCP server for fetching and extracting web content using Trafilatura. Runs locally from the fetchv2-mcp-server Python package.

not rated 3 changed 1mo ago A Socket: warn tokens not measured original MIT

paimon-mcp-fetch

05

paimonchan/paimon-mcp-fetch

MCP server Claude CodeCodexCursor +2

MCP server "paimon-mcp-fetch" as configured in paimonchan/paimon-mcp-fetch. Launched with https://github.com/paimonchan/paimon-mcp-fetch/releases/download/v0.1.2/paimon-m. Needs 4 environment variables to run.

not rated 3 5mo ago A tokens not measured original MIT

searchts

06

capad-xyz/searchts

MCP server Claude CodeCodexCursor +2

The missing layer between AI and the web. Open-source escalating unlocker (browser-fingerprinted fetch -> JS-render relay -> stealth browser) for read, keyless multi-provider search with rank fusion, subtitles-first video transcribe, and on-demand asset/design-inspiration grab (palette/fonts/assets through the same…

not rated 2 today A tokens not measured original MIT

jinaai-mcp-server

07

cyanheads/jinaai-mcp-server

MCP server Claude CodeCodexCursor +2

A Model Context Protocol (MCP) server that provides intelligent web reading capabilities using the Jina AI Reader API. It extracts clean, LLM-ready content from any URL. Runs locally from the @cyanheads/jinaai-mcp-server npm package.

not rated 1 1y ago A tokens not measured original Apache-2.0

mdingest

08

LOsioChico/mdingest

MCP server Claude CodeCodexCursor +2

MCP server "mdingest" as configured in LOsioChico/mdingest. Runs locally from the mdingest npm package.

not rated 1 1mo ago A tokens not measured original MIT

netlens

09

pzalutski-pixel/netlens-mcp

MCP server Claude CodeCodexCursor +2

Read any web page as clean, ad-stripped Markdown past robots.txt and bot blocks, plus web search. Runs locally from the netlens-mcp npm package. Needs 2 environment variables to run.

not rated 0 8d ago A tokens not measured original Apache-2.0

readable

10

tommypj/readable-mcp

MCP server Claude CodeCodexCursor +2

MCP server "readable" as configured in tommypj/readable-mcp. Launched with uv --directory /absolute/path/to/readable-mcp run readable-mcp.

not rated 0 3mo ago A tokens not measured original MIT

correctover

11

m8louist12-boop/mcp-server

MCP server Claude CodeCodexCursor +2

Legacy MCP security server — superseded by correctover-mcp-gateway for Claude Code, Cursor, Cline and Windsurf. Install the gateway instead; the runtime SDK is the correctover package. Runs locally from the correctover-mcp-server npm package.

not rated 0 4d ago A tokens not measured original Apache-2.0