Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Nimble MCP connector

Bearer TokenAISearch

Connect to Nimble MCP. Search the web across multiple engines, extract content from any URL, crawl websites at scale, discover all URLs on a site, and run...

Nimble MCP connector

  1. Install the SDK

    Section titled “Install the SDK”
    Terminal window
    npm install @scalekit-sdk/node

    Full SDK reference: Node.js | Python

  2. Set your credentials

    Section titled “Set your credentials”

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>

  3. Set up the connector

    Section titled “Set up the connector”

    Register your Nimble MCP credentials with Scalekit so it can authenticate requests on your behalf. You do this once per environment.

    Dashboard setup steps

    Generate an API key from your Nimble account so Scalekit can authenticate your users’ web intelligence requests.

    1. Create an API key in Nimble

      • Sign in to app.nimbleway.com.
      • In the left sidebar, click API Playground or look for the Create API Key item in the onboarding checklist at the bottom left.
      • Click Create API Key.

      In the Create API Key dialog:

      • Enter a Key name that identifies this integration, for example Agent Auth.
      • Click Create key.

      Nimble Create API Key dialog with key name "Agent Auth"

      Nimble displays your new API key. Copy it immediately — it is only shown once.

    2. Add the API key to Scalekit

      • In the Scalekit dashboard, go to AgentKit > Connections > Create Connection.
      • Search for Nimble MCP and click Create.
      • In the API Key field, paste the key you copied.
      • Click Save.

      Scalekit validates the key and marks the connection as active. Your users can now execute Nimble tools through their own connected accounts.

  4. Make your first call

    Section titled “Make your first call”
    quickstart.ts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    

    const scalekit = new ScalekitClient(
      process.env.SCALEKIT_ENV_URL,
      process.env.SCALEKIT_CLIENT_ID,
      process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    

    const connector = 'nimblemcp'
    const identifier = 'user_123'
    

    // Make your first call
    const result = await actions.executeTool({
      connector,
      identifier,
      toolName: 'nimblemcp_nimble_agents_list',
      toolInput: {},
    })
    console.log(result)

What you can do

Section titled “What you can do”

Connect this agent connector to let your agent:

  • Results nimble task — Get the status and results of an async task
  • Search nimble — Search the web using Nimble’s Search API with configurable content richness
  • Map nimble — Discover all URLs on a website by crawling its pages and sitemap
  • Async nimble extract — Start an asynchronous URL extraction
  • Extract nimble — Extract and parse content from a specific URL using Nimble’s Extract API
  • Terminate nimble crawl — Cancel a running or queued crawl job

Tool list

Section titled “Tool list”

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

nimblemcp_nimble_agent_run_async#Start an asynchronous agent run. Returns immediately with a task ID. Use this for long-running extractions using a pre-built or custom agent. Poll results with `nimblemcp_nimble_task_results`. When to use: - You want to run a specific Nimble agent asynchronously without blocking. - You have a long-running agent job where you will poll for results. When NOT to use: - You want a synchronous agent result — use `nimblemcp_nimble_agents_run` instead.5 params

Start an asynchronous agent run. Returns immediately with a task ID. Use this for long-running extractions using a pre-built or custom agent. Poll results with `nimblemcp_nimble_task_results`. When to use: - You want to run a specific Nimble agent asynchronously without blocking. - You have a long-running agent job where you will poll for results. When NOT to use: - You want a synchronous agent result — use `nimblemcp_nimble_agents_run` instead.

NameTypeRequiredDescription
agentstringrequiredName of the agent to run (from `nimblemcp_nimble_agents_list`).
paramsobjectrequiredRuntime input parameters for the agent.
callback_urlstringoptionalOptional webhook URL to receive results when the job completes.
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_agents_generate#Kick off generation of a new custom agent. Returns a `generation_id`; poll it with `nimblemcp_nimble_agents_status` to get the generated agent name. When to use: - You need a custom extraction agent for a site that isn't covered by the pre-built catalog. - You want to generate an agent from a natural-language prompt and an example URL. When NOT to use: - A pre-built agent already covers the site — use `nimblemcp_nimble_agents_run` instead.7 params

Kick off generation of a new custom agent. Returns a `generation_id`; poll it with `nimblemcp_nimble_agents_status` to get the generated agent name. When to use: - You need a custom extraction agent for a site that isn't covered by the pre-built catalog. - You want to generate an agent from a natural-language prompt and an example URL. When NOT to use: - A pre-built agent already covers the site — use `nimblemcp_nimble_agents_run` instead.

NameTypeRequiredDescription
promptstringrequiredNatural-language instruction describing what the agent should collect (e.g. 'Collect product name, price, and rating from Amazon product pages').
urlstringrequiredExample target URL that helps the generator understand page structure.
agent_namestringoptionalOptional desired name for the generated agent.
input_schemastringoptionalOptional JSON Schema object describing runtime input parameters.
output_schemastringoptionalOptional JSON Schema object describing desired output fields.
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_agents_get#Get full details of a specific agent including its input/output schema. Use after `nimblemcp_nimble_agents_list` to inspect an agent before running it. When to use: - You have an agent name and need to see its full schema before running it. When NOT to use: - You don't know the agent name — use `nimblemcp_nimble_agents_list` first.3 params

Get full details of a specific agent including its input/output schema. Use after `nimblemcp_nimble_agents_list` to inspect an agent before running it. When to use: - You have an agent name and need to see its full schema before running it. When NOT to use: - You don't know the agent name — use `nimblemcp_nimble_agents_list` first.

NameTypeRequiredDescription
agent_idstringrequiredExact agent name as returned by `nimblemcp_nimble_agents_list`.
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_agents_list#Browse the catalog of pre-built Nimble agents. Use this as the first step when you want to run a structured extraction on a known site or data source. When to use: - You want to discover available agents for a specific domain or data source. - You want to paginate through all agents in the catalog.5 params

Browse the catalog of pre-built Nimble agents. Use this as the first step when you want to run a structured extraction on a known site or data source. When to use: - You want to discover available agents for a specific domain or data source. - You want to paginate through all agents in the catalog.

NameTypeRequiredDescription
limitintegeroptionalMaximum number of agents to return in one page (1-100).
querystringoptionalShort keyword to filter agents by name or domain (e.g. 'amazon', 'linkedin'). Use 1-2 words for best results.
skipintegeroptionalOffset for pagination. Use 0 for the first page.
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_agents_run#Execute an agent against a target URL or set of parameters. Returns structured data synchronously. Use `nimblemcp_nimble_agents_list` to discover available agents. When to use: - You know the agent name and want its structured output inline. When NOT to use: - You want an async run — use `nimblemcp_nimble_agent_run_async` instead.4 params

Execute an agent against a target URL or set of parameters. Returns structured data synchronously. Use `nimblemcp_nimble_agents_list` to discover available agents. When to use: - You know the agent name and want its structured output inline. When NOT to use: - You want an async run — use `nimblemcp_nimble_agent_run_async` instead.

NameTypeRequiredDescription
agent_namestringrequiredAgent name from `nimblemcp_nimble_agents_list`, `nimblemcp_nimble_agents_get`, or a completed generation.
paramsobjectrequiredRuntime input parameters built from the agent's input_schema. Include all required keys.
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_agents_status#Check the current status of an agent generation. Status flow: in-progress → succeeded or failed. When to use: - You started a generation with `nimblemcp_nimble_agents_generate` or `nimblemcp_nimble_agents_update_from_agent` and want to check if it completed. When NOT to use: - You want crawl job status — use `nimblemcp_nimble_crawl_status`. - You want async task results — use `nimblemcp_nimble_task_results`.3 params

Check the current status of an agent generation. Status flow: in-progress → succeeded or failed. When to use: - You started a generation with `nimblemcp_nimble_agents_generate` or `nimblemcp_nimble_agents_update_from_agent` and want to check if it completed. When NOT to use: - You want crawl job status — use `nimblemcp_nimble_crawl_status`. - You want async task results — use `nimblemcp_nimble_task_results`.

NameTypeRequiredDescription
generation_idstringrequiredServer-assigned generation ID returned by `nimblemcp_nimble_agents_generate` or `nimblemcp_nimble_agents_update_from_agent`.
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_agents_update_from_agent#Create a refinement generation that starts from an existing agent. Returns a `generation_id`; poll with `nimblemcp_nimble_agents_status` to get the updated agent. When to use: - You want to modify an existing agent's behavior using natural-language instructions. - You want to extend an agent's output schema without rebuilding from scratch. When NOT to use: - You want to build a brand-new agent — use `nimblemcp_nimble_agents_generate`.4 params

Create a refinement generation that starts from an existing agent. Returns a `generation_id`; poll with `nimblemcp_nimble_agents_status` to get the updated agent. When to use: - You want to modify an existing agent's behavior using natural-language instructions. - You want to extend an agent's output schema without rebuilding from scratch. When NOT to use: - You want to build a brand-new agent — use `nimblemcp_nimble_agents_generate`.

NameTypeRequiredDescription
from_agentstringrequiredAgent name to refine. A new generation is created from this agent.
promptstringrequiredNatural-language refinement instruction (e.g. 'add a ratings field to the output').
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_crawl_list#List crawl jobs, optionally filtered by status. When to use: - You want to see all active or past crawl jobs in the account. - You want to filter crawls by their current status.4 params

List crawl jobs, optionally filtered by status. When to use: - You want to see all active or past crawl jobs in the account. - You want to filter crawls by their current status.

NameTypeRequiredDescription
limitintegeroptionalMaximum number of crawl jobs to return. Default is 20.
statusstringoptionalOptional status filter (e.g. "queued", "running", "succeeded", "failed", "canceled").
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_crawl_run#Start a web crawl to extract content from multiple pages on a website. The crawl discovers and visits pages starting from a given URL, following links up to the specified limit. Results are retrieved via `nimblemcp_nimble_crawl_status`. When to use: - You need to extract content from multiple pages on a site automatically. - You want link-following or sitemap-based URL discovery. When NOT to use: - You need content from a single known URL — use `nimblemcp_nimble_extract` instead. - You need results immediately — this is async; first pages complete ~1-2 min after dispatch.10 params

Start a web crawl to extract content from multiple pages on a website. The crawl discovers and visits pages starting from a given URL, following links up to the specified limit. Results are retrieved via `nimblemcp_nimble_crawl_status`. When to use: - You need to extract content from multiple pages on a site automatically. - You want link-following or sitemap-based URL discovery. When NOT to use: - You need content from a single known URL — use `nimblemcp_nimble_extract` instead. - You need results immediately — this is async; first pages complete ~1-2 min after dispatch.

NameTypeRequiredDescription
urlstringrequiredStarting URL for the crawl. The crawler discovers and visits linked pages from this entry point.
allow_external_linksbooleanoptionalWhether to follow links to external domains. Default is false.
allow_subdomainsbooleanoptionalWhether to follow links to subdomains of the starting URL. Default is false.
exclude_pathsstringoptionalOptional regex patterns. URLs matching any pattern will be skipped.
include_pathsstringoptionalOptional regex patterns. Only URLs matching at least one pattern will be crawled.
limitintegeroptionalMaximum number of pages to crawl (default: 100). Higher limits take longer but provide more coverage.
namestringoptionalOptional human-readable name for this crawl job.
sitemapstringoptionalHow to use the site's sitemap: "include" (default), "skip", or "only".
tool_descriptionstringoptionalOptional description of the tool's purpose.
tool_reasoningstringoptionalOptional reasoning about why this tool was selected.
nimblemcp_nimble_crawl_status#Check the status and progress of a running or completed crawl job. When to use: - You started a crawl with `nimblemcp_nimble_crawl_run` and want to check its progress or retrieve results. When NOT to use: - You want async task results from `nimble_extract_async` or `nimble_agent_run_async` — use `nimblemcp_nimble_task_results` for those.3 params

Check the status and progress of a running or completed crawl job. When to use: - You started a crawl with `nimblemcp_nimble_crawl_run` and want to check its progress or retrieve results. When NOT to use: - You want async task results from `nimble_extract_async` or `nimble_agent_run_async` — use `nimblemcp_nimble_task_results` for those.

NameTypeRequiredDescription
crawl_idstringrequiredThe unique crawl identifier returned by `nimblemcp_nimble_crawl_run`.
tool_descriptionstringoptionalOptional description of the tool's purpose.
tool_reasoningstringoptionalOptional reasoning about why this tool was selected.
nimblemcp_nimble_crawl_terminate#Cancel a running or queued crawl job. When to use: - You want to stop a crawl that is no longer needed before it completes. When NOT to use: - The crawl has already succeeded or failed — it cannot be cancelled in a terminal state.3 params

Cancel a running or queued crawl job. When to use: - You want to stop a crawl that is no longer needed before it completes. When NOT to use: - The crawl has already succeeded or failed — it cannot be cancelled in a terminal state.

NameTypeRequiredDescription
crawl_idstringrequiredThe unique crawl identifier to cancel.
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_extract#Extract and parse content from a specific URL using Nimble's Extract API. This is a synchronous call — it waits for extraction to complete before returning. When to use: - You have a specific URL and need its content immediately. - You want structured content (markdown, text) from a single page. When NOT to use: - You need to extract many pages — use `nimblemcp_nimble_crawl_run` instead. - The page loads slowly — use `nimblemcp_nimble_extract_async` for async extraction.8 params

Extract and parse content from a specific URL using Nimble's Extract API. This is a synchronous call — it waits for extraction to complete before returning. When to use: - You have a specific URL and need its content immediately. - You want structured content (markdown, text) from a single page. When NOT to use: - You need to extract many pages — use `nimblemcp_nimble_crawl_run` instead. - The page loads slowly — use `nimblemcp_nimble_extract_async` for async extraction.

NameTypeRequiredDescription
urlstringrequiredThe URL to extract content from.
countrystringoptionalCountry code for geo-targeted rendering (e.g. "us").
driverstringoptionalBrowser driver to use: "chrome" or "firefox". Omit for default.
localestringoptionalLocale code for localized rendering (e.g. "en-US").
output_formatstringoptionalOutput format: "markdown" (default) or "text".
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
waitstringoptionalExtra milliseconds to wait for dynamic content to load before extraction.
nimblemcp_nimble_extract_async#Start an asynchronous URL extraction. Returns immediately with a task ID. Poll `nimblemcp_nimble_task_results` to retrieve the extracted content when ready. When to use: - You want to extract a URL without blocking while it renders. - The page is complex or slow to load. When NOT to use: - You need the result inline — use `nimblemcp_nimble_extract` for synchronous extraction.9 params

Start an asynchronous URL extraction. Returns immediately with a task ID. Poll `nimblemcp_nimble_task_results` to retrieve the extracted content when ready. When to use: - You want to extract a URL without blocking while it renders. - The page is complex or slow to load. When NOT to use: - You need the result inline — use `nimblemcp_nimble_extract` for synchronous extraction.

NameTypeRequiredDescription
urlstringrequiredThe URL to extract content from.
callback_urlstringoptionalOptional webhook URL to receive results when extraction completes.
countrystringoptionalNo description.
driverstringoptionalBrowser driver to use: "chrome" or "firefox". Omit for default.
localestringoptionalNo description.
output_formatstringoptionalOutput format: "markdown" (default) or "text".
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
waitstringoptionalExtra milliseconds to wait for dynamic content.
nimblemcp_nimble_map#Discover all URLs on a website by crawling its pages and sitemap. Returns a flat list of URLs found on the site. Useful for understanding site structure before targeted extraction. When to use: - You need to enumerate the URL space of a site before deciding what to extract. - You want a quick snapshot of all discoverable links on a domain. When NOT to use: - You need the page content itself — use `nimblemcp_nimble_crawl_run` or `nimblemcp_nimble_extract`.6 params

Discover all URLs on a website by crawling its pages and sitemap. Returns a flat list of URLs found on the site. Useful for understanding site structure before targeted extraction. When to use: - You need to enumerate the URL space of a site before deciding what to extract. - You want a quick snapshot of all discoverable links on a domain. When NOT to use: - You need the page content itself — use `nimblemcp_nimble_crawl_run` or `nimblemcp_nimble_extract`.

NameTypeRequiredDescription
urlstringrequiredStarting URL. The mapper will discover all linked URLs from this entry point.
domain_filterstringoptionalOptional domain filter to restrict URL discovery.
limitstringoptionalMaximum number of URLs to return. Omit for no limit.
sitemapstringoptionalSitemap strategy: "include", "skip", or "only".
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.
nimblemcp_nimble_task_results#Get the status and results of an async task. Use this to retrieve results from `nimblemcp_nimble_extract_async` or `nimblemcp_nimble_agent_run_async` after initiating them. When to use: - You started an async extraction or agent run and want to poll for its results. When NOT to use: - You want crawl status — use `nimblemcp_nimble_crawl_status` for crawl jobs.3 params

Get the status and results of an async task. Use this to retrieve results from `nimblemcp_nimble_extract_async` or `nimblemcp_nimble_agent_run_async` after initiating them. When to use: - You started an async extraction or agent run and want to poll for its results. When NOT to use: - You want crawl status — use `nimblemcp_nimble_crawl_status` for crawl jobs.

NameTypeRequiredDescription
task_idstringrequiredThe task ID returned by `nimblemcp_nimble_extract_async` or `nimblemcp_nimble_agent_run_async`.
tool_descriptionstringoptionalNo description.
tool_reasoningstringoptionalNo description.