workingproxysites.

Provider integration · Official publisher

Decodo MCP

Decodo MCP exposes Web Scraping API tasks through a hosted connection. Toolset selection, response length and regional parameters are useful decisions to make before asking an agent to collect a batch of pages.

Server publisher: Decodo. Guide maintained by Working Proxy Sites.

Documentation reviewed · Next review

What you can use it for

  • Read a URL as Markdown.
  • Collect parsed search results.
  • Extract supported marketplace product details.

Documented capabilities: Web search · Scraping & extraction.

Account & usage

Account required
Yes
Required product
Decodo Web Data API.
Billing basis
Scraping usage is billed under the account plan; request features such as rendering and proxy pool affect consumption. Provider pricing.
Server software license
MIT

When to choose Decodo MCP

A useful fit when

  • Search followed by Markdown page retrieval.
  • Structured product collection through a supported target parser.

Check another approach when

  • A client that cannot attach the required custom authentication header.
  • Browser click-and-type automation: JavaScript rendering is a different capability.
Sources: Decodo official MCP repository, Decodo HTTP server implementation

Connect to Decodo MCP

Choose a connection profile below and replace credential placeholders in your own MCP client. The transport describes the MCP connection.

Hosted MCP

Streamable HTTP · hosted

Endpoint
https://mcp.decodo.com/mcp
Authentication
Authorization: Bearer followed by a Web Data API key (recommended). Authorization: Basic with a basic authentication token still works for older plans.

Before you connect

  • Decodo Web Data API subscription and API key (older plans: basic authentication token).
  • A remote MCP client that accepts custom headers.

Cursor mcp.json (JSON) Sources: Decodo official MCP repository, Decodo HTTP server implementation, Cursor MCP configuration reference

Cursor: .cursor/mcp.json (project) or ~/.cursor/mcp.json (global). Configuration guide.

{
  "mcpServers": {
    "decodo": {
      "url": "https://mcp.decodo.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Build a focused search and extraction task

A suggested sequence using the documented tools. Check the connected server's tool schema before making a call.

  1. Choose the retrieval surface

    Use google_search to find pages, or amazon_product for a supported product record. Decide which output the task needs before collecting it.

    Tools: google_search, amazon_product

    Sources: Decodo official MCP repository

  2. Read source pages with explicit options

    Use scrape_as_markdown for chosen URLs. Set geo and locale deliberately; request jsRender when the content requires JavaScript rendering.

    Tools: scrape_as_markdown

    Sources: Decodo official MCP repository

  3. Check completeness before summarizing

    Inspect whether a response was truncated. Adjust tokenLimit for the next retrieval only when your client can handle the larger output. Keep the source URL with the summary.

    Tools: scrape_as_markdown

    Sources: Decodo official MCP repository

Selected tools & example tasks

Troubleshoot the connection

The response stops before the page ends.

Check tokenLimit and truncation before concluding that the source lacks the content. Increase the permitted response size where appropriate.

Sources: Decodo official MCP repository

The retrieved page shows a different region.

Review geo, locale and any supported target domain separately. A language request alone does not specify all regional retrieval settings.

Sources: Decodo official MCP repository

Limits & undocumented behavior

  • The toolsets parameter restricts which tools are exposed; all tools are registered when it is omitted.
  • JavaScript rendering is documented, but this listing does not infer an interactive browser-control capability.
  • The reviewed tool documentation does not establish proxy purchasing or proxy account management.

Decodo MCP: questions & answers

How do I limit which Decodo tools an agent sees?

Use the documented toolsets query parameter. Omitting it exposes all registered toolsets; specify groups when you need a focused tool list.

Sources: Decodo official MCP repository, Decodo HTTP server implementation
Can Decodo MCP click through an interactive website?

The documented jsRender option requests JavaScript rendering. It is not a documented browser interaction interface with click and type tools.

Sources: Decodo official MCP repository
Can I reuse every scraping option with every structured target?

Check the selected target. Parameter support varies: the repository documents exceptions for structured parsers, so a working generic page request does not establish compatibility with every product or search tool.

Sources: Decodo official MCP repository

Sources & review history

This listing is documentation-confirmed. We reviewed the primary sources below; this does not establish successful tool execution.

Record updated . Review due .

  1. Decodo official MCP repositoryChecked · Publisher, hosted setup, credentials, toolsets, tool names and MIT license
  2. Decodo HTTP server implementationChecked · Streamable HTTP transport on the hosted /mcp route
  3. Decodo scraping plansChecked · Product requirement and feature-dependent request billing
  4. Cursor MCP configuration referenceChecked · Client JSON format and remote header support

Spotted a change? Send the source and the affected setup step to our contact address.

Alternatives to Decodo MCP

These integrations share documented capabilities with Decodo MCP. Compare their setup and product requirements for your task.

Apify MCP

Find Apify Actors, inspect their inputs and pricing, run a selected Actor, and retrieve its dataset through the official MCP server.

Shared capabilities
Web search · Scraping & extraction
Connection choices
Streamable HTTP · Local stdio
Product to check
Apify Actors and platform usage
Compare setup & authentication →

Bright Data MCP

Search the public web, retrieve page content and use optional browser tools through Bright Data’s hosted or local MCP integration.

Shared capabilities
Web search · Scraping & extraction
Connection choices
Streamable HTTP · Local stdio
Product to check
Bright Data Web Unlocker API; additional products may be used by optional tools.
Compare setup & authentication →

Evomi MCP

Inspect Evomi proxy products, targeting and usage, rotate sessions, and run scraping jobs through a local Python MCP server.

Shared capabilities
Web search · Scraping & extraction
Connection choices
Local stdio
Product to check
Evomi Public API access plus the proxy or Scraper API product used by the tool.
Compare setup & authentication →

Exa MCP

Connect Exa MCP for web search, known-page fetching and authenticated research. Choose tool exposure, account access and how to resume an active Agent run.

Shared capabilities
Web search · Scraping & extraction
Connection choices
Streamable HTTP
Product to check
Rate-limited hosted search/fetch without an account. OAuth or a team API key enables account usage and the hosted Agent tool.
Compare setup & authentication →