Fusion Proxy MCP server
OfficialThis server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Fusion Proxy MCP server: web access for AI agents through residential proxies
An MCP server that lets Claude, Cursor, VS Code Copilot and any other MCP client fetch web pages through residential IPs in the country you choose. Useful when an agent gets blocked, rate-limited, or needs to see a page the way a visitor from another country sees it.
Tools
Tool | What it does |
| Downloads a public page through a residential IP and returns it as Markdown (default), plain text or HTML |
| Shows the IP, city, country and network that websites see |
country: two-letter code (us,de,jp, ...). Leave it out for any country.session: any name. Calls with the same name keep the same IP for 10 minutes, so an agent can browse several pages of one site as one visitor.
Example conversation:
You: What does the pricing page of example.com show to visitors from Japan?
The agent calls
fetch_page(url="https://example.com/pricing", country="jp")and reads the Markdown.
Tested output from a real session:
check_exit_ip {'country': 'jp'} -> IP 60.85.55.0, Tokyo, Tokyo, JP (AS17676 SoftBank Corp.)
check_exit_ip {'country': 'us', 'session': 'a'} -> IP 47.156.138.80, Walnut, California, US (AS5650 Verizon Business)
check_exit_ip {'country': 'us', 'session': 'a'} -> IP 47.156.138.80, Walnut, California, US (AS5650 Verizon Business)
fetch_page(https://quotes.toscrape.com/, country=gb) -> Status: 200 ... # [Quotes to Scrape](/) ...Related MCP server: DataImpulse MCP Proxy
Setup
You need Fusion Proxy credentials (username and password from the dashboard; there is a free trial) and uv (or pip).
Claude Code
claude mcp add fusionproxy -e FUSION_USER=your_username -e FUSION_PASS=your_password \
-- uvx --from git+https://github.com/fusion-proxy/fusionproxy-mcp fusionproxy-mcpClaude Desktop
claude_desktop_config.json (Settings, Developer, Edit Config):
{
"mcpServers": {
"fusionproxy": {
"command": "uvx",
"args": ["--from", "git+https://github.com/fusion-proxy/fusionproxy-mcp", "fusionproxy-mcp"],
"env": { "FUSION_USER": "your_username", "FUSION_PASS": "your_password" }
}
}
}Cursor
~/.cursor/mcp.json: the same mcpServers block as for Claude Desktop.
VS Code
.vscode/mcp.json:
{
"servers": {
"fusionproxy": {
"type": "stdio",
"command": "uvx",
"args": ["--from", "git+https://github.com/fusion-proxy/fusionproxy-mcp", "fusionproxy-mcp"],
"env": { "FUSION_USER": "your_username", "FUSION_PASS": "your_password" }
}
}
}Without uv
pip install git+https://github.com/fusion-proxy/fusionproxy-mcp
fusionproxy-mcp # speaks MCP over stdio; point your client's "command" at itSettings
Variable | Required | Meaning |
| yes | Proxy username (main user or a sub-user) |
| yes | Proxy password |
| no | Default country when a call does not pass one |
| no | Gateway |
Traffic through the server counts against your residential plan like any other request. A typical HTML page is 50 KB to 2 MB.
How it works
Each call opens a connection to the Fusion Proxy gateway with the options in the username (-country-jp, -sessid-...-sessTime-600s), downloads the page with a normal browser User-Agent, follows redirects and converts HTML to Markdown with html2text. If a residential connection drops, the call retries once on a new connection. Only http and https URLs are accepted.
The server does not run JavaScript. For pages that render in the browser, see playwright-proxy.
Works with the MCP Python SDK 1.x and 2.x.
Use responsibly
Fetch public pages only, respect the sites' terms and robots.txt, and keep the request rate reasonable.
Related
fusionproxy: code examples in 8 languages
python-web-scraping: a requests + BeautifulSoup scraper
Residential proxies from $2.95/GB
License
MIT, see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Live web search results and web pages as Markdown; page fetches use a residential network.
Private web fetch and egress through residential IPs in many countries on URnetwork.
MCP server (stdio): fetch web pages as clean readable markdown via the AgentForge API
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables AI assistants to crawl websites, extract dynamic content, navigate links, and save structured Markdown files via the MCP protocol, with support for anti-bot bypass, CSS selectors, and custom JavaScript execution.1110 PyPI45MIT
- AlicenseBqualityDmaintenanceEnables fetching public HTTP(S) pages through DataImpulse residential proxies with country, city, and session targeting, plus an exit IP check tool. Includes best-effort SSRF safeguards and response size limits for safe bounded access.224MIT
- FlicenseBqualityBmaintenanceEnables MCP-compatible AI clients to extract live web content and convert it into structured Markdown for LLM ingestion, RAG pipelines, and agentic workflows.16-
- AlicenseAqualityCmaintenanceGives MCP clients such as Claude Code, Claude Desktop, Cursor or Codex a read_page tool that fetches a web page and returns only its main content as lean Markdown, stripped of navigation, ads and tracking. Accepts optional focus, links and country arguments so a client can pull just the sections relevant to a question, shorten same-site links, or read pages as they appear in a given country.1MIT