1cent Web Intelligence

by maxzoa

SSE

360 downloads

Not rated

GitHub Website

About

Production remote MCP server with 35 safe web-intelligence tools: 32 paid x402 URL operations plus 3 free discovery/demo tools. Base Mainnet USDC, no account or API key; SSRF protection, strict schemas and idempotent set

Details

Author: maxzoa
Downloads: 360
Transport: SSE
Categories: Web Scraping, AI, Security

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name 1cent Web Intelligence

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

From the repository

{
  "mcpServers": {
    "1cent": {
      "type": "http",
      "url": "https://1cent.maxzoa.ru/mcp"
    }
  }
}

`catalog.tools.search`

Start here before choosing a paid operation. Search the local 1cent catalog without fetching a URL or requiring payment. Returns up to five matching tools with purpose, current atomic Base USDC price and REST path.

`demo.url.pulse`

Return a precomputed example of 1cent URL Pulse output without payment, database access or any network request. This fixed demonstration never accepts a URL and never fetches an external resource.

`demo.live.pulse`

Run the real SSRF-protected URL Pulse service against the fixed https://example.com/ target without payment. The tool accepts no URL, is rate-limited per client and preserves normal cache and audit behavior.

`web.url.pulse`

Check a public HTTP or HTTPS URL before expensive browsing or AI processing. Returns availability, redirects, content type, page metadata, language, cache state, content hash, robots policy, and access restrictions. Does not execute JavaScript. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cache; set fresh=true only when a new upstream fetch is required.

`web.url.passport`

Inspect a public HTTP or HTTPS URL and return a structured site passport. Includes pulse fields, registrable domain, robots and sitemap discovery, feeds, OpenAPI hints, and page metadata. Uses at most eight external HTTP requests and does not execute JavaScript. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cache; set fresh=true only when a new upstream fetch is required.

`web.url.extract`

Extract normalized main text and optional links from a public HTTP or HTTPS document. Returns title, author, publication time, language, content hash, truncation and cache state. Output size and fetch time are bounded; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Set include_links=true only when normalized links are needed. Keep fresh=false to reuse cache.

`web.url.changed`

Compare a public HTTP or HTTPS URL with its previously stored normalized content hash. Creates a baseline on first use, then reports whether content changed and returns current and previous hashes with timestamps. JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cache; set fresh=true only for a new fetch.

`web.url.status`

Check HTTP reachability, status and final URL. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.redirects`

Return the safely validated redirect chain. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.headers`

Return allowlisted response headers only. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.timing`

Return measured end-to-end fetch timing. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.content_type`

Classify MIME type, charset and bounded content length. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.canonical`

Resolve requested, final and declared canonical URLs with evidence. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.language`

Report declared and heuristically detected document language. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.hash`

Compute a versioned SHA-256 of normalized content. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.metadata`

Extract title, description, author, dates and canonical metadata. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.social_cards`

Extract bounded Open Graph and Twitter Card fields. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.jsonld`

Extract bounded JSON-LD blocks without executing scripts. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.headings`

Return the bounded heading hierarchy from h1 through h6. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.word_stats`

Estimate words, characters, sentences and reading time. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.links`

Extract up to 200 normalized safe links. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.images`

List up to 100 image references without downloading images. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.text`

Return bounded normalized readable text. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.markdown`

Convert readable HTML content to bounded Markdown. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.rag_chunks`

Split readable text into deterministic bounded RAG chunks. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.diff`

Return a bounded normalized diff against the previous snapshot. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.site.robots`

Fetch and parse the origin robots.txt policy. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.site.sitemaps`

Discover up to five bounded sitemap resources. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.site.feeds`

Discover declared RSS and Atom feeds. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.site.llms_txt`

Return bounded llms.txt text when publicly available. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.site.security_txt`

Parse public security.txt fields without following contacts. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.site.openapi`

Discover and summarize bounded public OpenAPI documents. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.security_headers`

Assess common response security headers as static evidence. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.tls`

Inspect the public HTTPS certificate on port 443. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

`web.url.access_flags`

Report heuristic authentication, paywall and JavaScript access flags. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "1cent web intelligence": {
            "1cent": {
                "type": "http",
                "url": "https://1cent.maxzoa.ru/mcp"
            }
        }
    }
}

McpServers

{
    "1cent": {
        "type": "http",
        "url": "https://1cent.maxzoa.ru/mcp"
    }
}

Give AI agents safe, bounded web intelligence without subscriptions, API keys or handing a crawler unrestricted network access. Start with three free MCP tools; pay only for the URL operation used. Production uses x402 v2, Base Mainnet USDC and PayAI.

Try the real safe fetch path in one command — fixedexample.com, no payment:

curl -sS https://1cent.maxzoa.ru/v1/demo/live-pulse

Or preview one URL of your choice without payment, limited to one preview per client and UTC day:

curl -sS "https://1cent.maxzoa.ru/v1/demo/preview?url=https%3A%2F%2Fexample.com%2F"

- MCP:https://1cent.maxzoa.ru/mcp
- Free product demo:https://1cent.maxzoa.ru/v1/demo/pulse
- Free live demo:https://1cent.maxzoa.ru/v1/demo/live-pulse
- Live catalog/prices:https://1cent.maxzoa.ru/v1/catalog
- Public trust status:https://1cent.maxzoa.ru/status.json
- Buyer guide:https://1cent.maxzoa.ru/docs/getting-started
- Browser purchase entry:https://1cent.maxzoa.ru/try
- Outcome packages:https://1cent.maxzoa.ru/v1/products

Release 0.8.1 exposes 43 paid REST/MCP operations plus three free MCP tools:

- catalog.tools.search— find the correct operation and live price without a URL fetch;
- demo.url.pulse— inspect a fixed precomputed output sample without payment or network access.
- demo.live.pulse— run the real safe service against fixedexample.com, rate-limited.

Public MCP discovery uses navigable dot-notation (web.url.status,web.site.openapi,web.batch.url_status). Pre-0.6 underscore names remain accepted as compatibility aliases but are intentionally omitted fromtools/list.

MCP also publishes one buyer prompt (choose_url_tool) and one static buyer-guide resource (onecent://buyer-guide). Every input field includes constraints, examples and machine-readable descriptions so agents can choose and call tools correctly on the first attempt.

- Official MCP Registry:ru.maxzoa/1cent;
- Glama remote connector:https://glama.ai/mcp/connectors/ru.maxzoa/1cent;
- Smithery:https://smithery.ai/servers/maxzoa27/onecent;
- MCP.so:https://mcp.so/servers/1cent;
- LobeHub:https://lobehub.com/mcp/maxzoa-1cent.
- MCPServers.org:https://mcpservers.org/ru/servers/maxzoa/1cent.

Glama release verification uses the repository'sonecent-glamastdio entry point. It loads the same MCP tool registry as production for schema inspection; it does not provide a payment bypass or a second implementation of paid URL operations.

Directory status is checked with dated evidence inMarketplace quality report. A page returning HTTP 200 alone is not counted as a successful listing: it must be searchable, current and installable.

Buyer setup starts with a no-payment diagnostic:

Generate or install a secret-free MCP client configuration:

onecent install --client claude onecent install --client cursor --apply onecent install --client vscode --apply onecent install --client codex

For MCP clients without native x402 signing, install the local Buyer Bridge:

pipx install "onecent[buyer]==0.8.1" onecent wallet set onecent bridge

Manual one-call approval is the default and has no commercial daily quota. The OS keyring holds the buyer secret; 1cent, remote MCP and catalog services never receive it. UNKNOWN outcomes are never retried. SeeBuyer Bridgefor Claude, Cursor, VS Code and Codex setup.

The direct CLI also refuses a paid call unless the buyer explicitly supplies a maximum amount, confirms Base Mainnet and types the one-call confirmation. Seeexamples/buyer-pythonandexamples/buyer-node.

Node buyers can install the public release package:

npm install --global onecent-buyer@0.8.1 onecent-buyer doctor

The package source remains available in packages/onecent-buyer. Registry pages:PyPIonecent0.8.1and npmonecent-buyer0.8.1.

The bounded batch tool accepts one to five distinct public URLs. Its x402 quote is the live unit price multiplied by the validated URL count before any URL fetch begins. Results retain input order and use an explicit partial-failure contract; UNKNOWN payments are never retried.

The product denominator, including planned, externally blocked and unsafe outcomes, is published in WEB_INTELLIGENCE_COVERAGE_MATRIX.mdwith JSON and CSV.

onecent watchprovides finite, capped change monitoring. It is disabled by default, requires explicit Base network/asset/seller confirmations and stops on UNKNOWN without creating a new payment attempt.

PostgreSQL is the runtime source for tool availability and atomic Base USDC prices. Config values are clean-install fallbacks. Paid URL work begins only after successful payment checks.

- public HTTP/HTTPS only; private, loopback, link-local and rebinding destinations fail closed;
- strict input schemas; unknown fields rejected;
- bounded redirects, response bodies, extracted text, concurrency and queue depth;
- payment identifier, request fingerprint and idempotent replay protection;
- UNKNOWN settlement never retried automatically;
- no seller private key, buyer key, Docker socket or JavaScript execution on the server;
- Streamable HTTP host/origin protection enabled for remote MCP.
- optional signed x402 offers and settlement receipts use a dedicated Ed25519did:webkey; they never expose or reuse a buyer or seller private key.

python -m venv .venv .venv/Scripts/pip install --require-hashes -r requirements-dev.lock .venv/Scripts/pip install --no-deps -e . ruff check . mypy pytest -q python scripts/validate_release.py docker compose --env-file .env.example config docker compose --env-file .env.example build pip-audit --no-deps -r requirements.lock --progress-spinner off

Copy.env.exampleto.env, replace placeholders, keepX402_ENVIRONMENT=testnetandX402_NETWORK=eip155:84532, then:

docker compose up -d --build docker compose ps

Container UID/GID:10001:10001. No host bind-mounted writable directory is required. This local example is intentionally testnet. Production mainnet activation requires owner approval, a fresh PostgreSQL backup, production preflight, development bypass disabled and rollback readiness.

- Current production state
- Documentation map
- Public REST API
- Remote MCP server
- Buyer quickstart
- Local MCP Buyer Bridge
- Security policy
- Release history
- Marketplace quality report
- Scaling and trust gates
- Production operations
- Incident response

Licensed under Apache-2.0. See LICENSEand NOTICE.

Enable AI agents to get structured data from unstructured web with AgentQL.

Web scraping, crawling, and change detection with AI

Official Apify MCP server for AI agents to run Actors, extract website data, and automate web scraping and crawling workflows.

1GB Free Trial, World's Leading Proxy Service Platform, Efficient Data Collection

Discover, extract, and interact with the web - one interface powering automated access across the public internet.

Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)

Easy web data access. Simplified retrieval of information from websites and online sources.

Adds powerful web scraping and search capabilities to LLM clients like Cursor and Claude.

Real-time web data, structured for agents

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

catalog.tools.search

demo.url.pulse

demo.live.pulse

web.url.pulse

web.url.passport

web.url.extract

web.url.changed

web.url.status

web.url.redirects

web.url.headers

web.url.timing

web.url.content_type

web.url.canonical

web.url.language

web.url.hash

web.url.metadata

web.url.social_cards

web.url.jsonld

web.url.headings

web.url.word_stats

web.url.links

web.url.images

web.url.text

web.url.markdown

web.url.rag_chunks

web.url.diff

web.site.robots

web.site.sitemaps

web.site.feeds

web.site.llms_txt

web.site.security_txt

web.site.openapi

web.url.security_headers

web.url.tls

web.url.access_flags

Claude Desktop / Cursor

McpServers

Install

More like this

@mendableai/firecrawl Mcp Server

Puppeteer

Context 7

1Panel

Playwright

🔎 GPT Researcher

`catalog.tools.search`

`demo.url.pulse`

`demo.live.pulse`

`web.url.pulse`

`web.url.passport`

`web.url.extract`

`web.url.changed`

`web.url.status`

`web.url.redirects`

`web.url.headers`

`web.url.timing`

`web.url.content_type`

`web.url.canonical`

`web.url.language`

`web.url.hash`

`web.url.metadata`

`web.url.social_cards`

`web.url.jsonld`

`web.url.headings`

`web.url.word_stats`

`web.url.links`

`web.url.images`

`web.url.text`

`web.url.markdown`

`web.url.rag_chunks`

`web.url.diff`

`web.site.robots`

`web.site.sitemaps`

`web.site.feeds`

`web.site.llms_txt`

`web.site.security_txt`

`web.site.openapi`

`web.url.security_headers`

`web.url.tls`

`web.url.access_flags`