What is novada-proxy?

A proxy service for AI agents that sends web requests through real residential internet connections. It can fetch, crawl, search, extract, map, research, and render web pages, with location selection and provider support.

Use it for web scraping, site research, location-specific requests, batch URL work, and pages that require JavaScript rendering.

It helps when direct requests are blocked by anti-bot systems or when results need to come from a particular country or city.

novada-proxy — Skill for Claude Code and Codex by NovadaLabs: A proxy service for AI agents that sends web…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/novadalabs/novada-proxy/proxy4agent

Any agent

npx skills add NovadaLabs/novada-proxy --skill proxy4agent

Clone the repo

git clone --depth 1 https://github.com/NovadaLabs/novada-proxy

Made for: Claude Code, Codex.

Or install novada-proxy, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/novadalabs/novada-proxy/proxy4agent.svg)](https://agentmods.dev/skills/novadalabs/novada-proxy/proxy4agent)

Your own site

<a href="https://agentmods.dev/skills/novadalabs/novada-proxy/proxy4agent"><img src="https://agentmods.dev/badge/skills/novadalabs/novada-proxy/proxy4agent.svg" alt="Measured on agentmods" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,429 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00078	$0.01429
Opus 5	$0.00039	$0.00714
Sonnet 5	$0.00016	$0.00286
Haiku 4.5	$0.00008	$0.00143

Measured 3d ago against content hash 546c48812b08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

novada-proxy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

clawhub/proxy4agent/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Novada Proxy

Residential proxy MCP server for AI agents. Route HTTP requests through 2M+ real home devices to bypass anti-bot systems, geo-target by country or city, maintain sticky sessions, and cache responses to save proxy credits.

npm: novada-proxy-mcp | GitHub: NovadaLabs/Novada-proxy

Setup

You only need credentials for ONE provider. Novada is the default and recommended provider.

Novada (recommended)

claude mcp add novada-proxy-mcp \
  -e NOVADA_PROXY_USER=your_username \
  -e NOVADA_PROXY_PASS=your_password \
  -- npx -y novada-proxy-mcp

Get credentials: novada.com → Dashboard → Residential Proxies (free tier, no credit card).

Any HTTP proxy (BrightData, Smartproxy, Oxylabs, IPRoyal...)

claude mcp add novada-proxy-mcp \
  -e PROXY_URL="http://user:pass@host:port" \
  -- npx -y novada-proxy-mcp

Optional credentials

NOVADA_API_KEY — enables novada_proxy_search (Google search)
NOVADA_BROWSER_WS — enables novada_proxy_render (JS rendering via real Chromium)
NOVADA_PROXY_ZONE — proxy type: res (residential, default), isp (rotating ISP), dcp (datacenter)

When to use which tool

Scrape a single URL         → novada_proxy_fetch
Need structured fields      → novada_proxy_extract
Scrape 2-20 URLs at once    → novada_proxy_batch_fetch
Discover URLs on a page     → novada_proxy_map → novada_proxy_batch_fetch
Crawl a whole site          → novada_proxy_crawl (recursive BFS, depth 1-5)
Login + multi-page flow     → novada_proxy_session (same session_id)
Search the web              → novada_proxy_search
JS-heavy SPA / blank page   → novada_proxy_render
Check proxy health          → novada_proxy_status

9 Tools

novada_proxy_fetch

Fetch any URL through a residential proxy. Returns structured JSON with content, status, and metadata. Responses are cached 300s by default — repeated calls cost zero credits (meta.cache_hit: true).

Read the full file on GitHub · 130 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 130 lines · 78 tokens per session scan A 546c48812b08

Subscribe to this mod's changes

novada-proxy is a skill published in the GitHub repository NovadaLabs/novada-proxy (4 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 1,429 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation Research ai-agents cloudflare-bypass geo-targeting mcp mcp-server novada

proxy4agent

Residential proxy for AI agents — fetch any URL through 2M+ real IPs, bypass anti-bot, geo-target, sticky sessions.

Goldentrii/proxy4agent · 33 tokens

chrome-devtools-cli

Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.

ChromeDevTools/chrome-devtools-mcp · 31 tokens

cookie-debugging

Uses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and cookie consent compliance. Use when diagnosing 401/403 errors, authentication redirects, session expiration, Cookie/Set-Cookie header issues, cookie banner consent conformance, or third-party…

ChromeDevTools/chrome-devtools-mcp · 71 tokens

chrome-devtools

Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).

ChromeDevTools/chrome-devtools-mcp · 55 tokens

2-repro-issue

Reproduce a single LinkedIn-MCP issue locally on the current branch against the real authenticated LinkedIn session at /.linkedin-mcp/profile/, using the MCP streamable-http server. Captures the exact failure mode (tool output, error, missing data) and maps it back to the scraper code path. Use when the user says…

stickerdaniel/linkedin-mcp-server · 75 tokens

ddgs

Use when an agent needs to search the web, find images/news/videos/books, or extract content from a URL. Covers the ddgs Python library, CLI, and MCP server integration.

deedy5/ddgs · 40 tokens