workingproxysites.
[ new post ]
[ menu ]

directory

boards

[all]

information

Provider integration · Official publisher

Nimble MCP

Nimble MCP separates three useful decisions: search when the source is unknown, map when the website is known, and extract when the URL is already selected. This makes it possible to keep discovery broad while limiting the pages brought into the assistant.

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

Documentation reviewed · Next review

What you can use it for

  • Discover candidate sources across the web.
  • Map website URLs before extraction.
  • Read content from a selected URL.

Documented capabilities: Web search · Scraping & extraction.

Account & usage

Account required
Yes
Required product
Nimble API usage
Billing basis
The published API model charges for successful requests, with different rates by product. Search depth and requested content can affect search cost. Managed Data Services plans and research-agent task pricing are separate considerations. Provider pricing.

When to choose Nimble MCP

A useful fit when

  • Research that begins without a source URL.
  • Selecting pages from a known website before reading their content.

Check another approach when

  • Assuming a list of search hits is already a verified research conclusion.
  • Fetching full content for every result when only URLs are needed.
Sources: Nimble official MCP tool declarations, Nimble official search reference

Connect to Nimble MCP

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

Nimble hosted MCP

Streamable HTTP · hosted

Endpoint
https://mcp.nimbleway.com/mcp
Authentication
Send a Nimble API key as a Bearer credential. Nimble also documents OAuth through supported plugin installation.

Before you connect

  • An account and API credential for the service.
  • A client with Streamable HTTP support.

Cursor mcp.json — replace the credential placeholder Sources: Nimble MCP reference

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

{
  "mcpServers": {
    "nimble-http": {
      "url": "https://mcp.nimbleway.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_NIMBLE_API_KEY"
      }
    }
  }
}

Discover first, then read selected pages

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

  1. Choose the discovery route

    Search for sources if the location is unknown. Map the site if the task already names a website. Review the returned candidate URLs.

    Tools: nimble_search, nimble_map

    Sources: Nimble official MCP tool declarations

  2. Read the selected evidence

    Extract a small set of relevant URLs. Compare the returned content with the question and retain the source links with the findings.

    Tools: nimble_extract

    Sources: Nimble MCP reference, Nimble official MCP tool declarations

  3. Adjust scope before expanding

    Choose the available search depth and result count to fit the task, then review the account cost of retrieving more content.

    Tools: nimble_search

    Sources: Nimble official search reference, Nimble API pricing reference

Selected tools & example tasks

Troubleshoot the connection

A copied connection uses /sse or Basic authentication.

Use the current MCP guide: /mcp with Streamable HTTP and the API key in an Authorization: Bearer header.

Sources: Nimble MCP reference

Limits & undocumented behavior

  • Available parameters should be checked in the client-discovered tool schema.
  • Search, extraction and research-agent work have different billing bases.
  • The configuration and tool names are documentation-confirmed; no authenticated connection was tested.

Nimble MCP: questions & answers

What is the difference between map and extract?

Map discovers URLs on a site. Extract reads a URL already chosen for inspection. Mapping first helps keep a multi-page job bounded.

Sources: Nimble official MCP tool declarations
Must I install the complete Nimble plugin?

No. The manual MCP connection is documented separately. The plugin adds skills and installation support around the service.

Sources: Nimble MCP reference, Nimble connection and plugin guide
Does every Nimble operation have one fixed request price?

No. The rate card distinguishes products, search depth, additional content and research-agent effort. Review the relevant operation before expanding usage.

Sources: Nimble API pricing reference

Sources & review history

This listing is documentation-confirmed. We reviewed the primary sources below; this is not a successful live connection test.

Record updated . Review due .

  1. Nimble MCP referenceChecked · Streamable HTTP endpoint, Bearer configuration and tool families.
  2. Nimble official MCP tool declarationsChecked · Exact nimble_search, nimble_extract and nimble_map tool names; capability distinctions.
  3. Nimble connection and plugin guideChecked · API-key setup, OAuth installation and optional skill bundle.
  4. Nimble API pricing referenceChecked · Product-specific usage, successful requests and managed plans.

Spotted a change? Share the source and the affected setup step in Site Feedback.

Alternatives to Nimble MCP

These integrations share documented capabilities with Nimble 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 →

Decodo MCP

Retrieve pages, search results and supported structured targets through Decodo’s Web Scraping API.

Shared capabilities
Web search · Scraping & extraction
Connection choices
Streamable HTTP
Product to check
Decodo Web Scraping API.
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 →