Find Similar Pages with Exa | BlockRun

Give Exa a reference webpage URL and optionally choose how many results to request. Receive related-page titles and links to explore, with the supplier’s returned similarity scores for reference.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use `exa-find-similar-blockrun` to find pages related to my reference URL. Ask for the URL if it is missing and pass it in body.url. Use body.numResults for my requested count, or the documented default 10 if I do not specify one. Reuse my Toolmu connection, or follow https://toolmu.com/SKILL.md if setup is needed. Work within my current budget and authorization. Show the returned page titles, URLs and supplier scores in the returned order, preserving missing author information. Report count shortfalls without treating the scores as percentages or independently verified quality ratings.

Task:
Find up to [number] pages like [webpage link]. Show their titles and links.

Paste into your connected AI's conversation.

Connection guide

Up to 0.01452 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

BlockRun

Find Similar Pages with Exa | BlockRun

Give Exa a reference webpage URL and optionally choose how many results to request. Receive related-page titles and links to explore, with the supplier’s returned similarity scores for reference.

You receive

You receive a collection of pages found in relation to your reference URL. The returned records provide page titles, links and supplier similarity scores, with author information when supplied. Your Agent can put these details into a reading list, keeping the scores as returned so you can inspect the candidate pages.

Start with your task

Find up to [number] pages like [webpage link]. Show their titles and links.

What to know

The search can return fewer pages than requested. Similarity does not establish accuracy, authority, completeness or freshness. Results may come from the reference website or another domain. The scores should not be interpreted as percentages, accuracy ratings or a universal quality ranking.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Similarity request`body`	`object`	Required	Required request object containing the reference URL and an optional result count. Required fields `url`
Reference URL`body.url`	`string`	Required	Required URL of a concrete webpage used as the reference for finding related pages. This is a page reference, not a keyword query.
Requested result count`body.numResults`	`number`	Optional	Optional requested count. The supplier documents whole numbers from 1 to 100 and a default of 10; fewer pages may be returned.

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "description": "Reference URL â pages similar to this will be returned."
        },
        "numResults": {
          "type": "number",
          "description": "Number of results to return (default 10, max 100)."
        }
      }
    }
  },
  "additionalProperties": false
}

Result schema

No fixed output contract is available. Field types reflect saved result evidence; individual responses can differ.

Result schema
Field / Path	Type	Meaning
Related pages`result.results`	`array`	Collection of pages returned for similarity to the reference URL. The collection size is not guaranteed to equal the requested count.
Page URL`result.results[].url`	`string`	Returned page link for inspecting a potentially related source. It can belong to the reference domain or a different domain.
Page title`result.results[].title`	`string`	Title supplied for the matched page. It identifies the result without validating the page or its publisher.
Supplier similarity score`result.results[].score`	`number`	Numeric score supplied with the match. Keep the value as returned; do not assume a percentage, accuracy threshold or comparison direction.
Author information`result.results[].author`	`null`	Author metadata when supplied. Null means no author information was provided for that record; do not invent a name.

Additional notes

Scope of the lookup

The BlockRun Exa endpoint documentation describes this operation as finding pages similar to a reference URL. Choose a concrete webpage as the starting point; the lookup does not map the entire website.

Use the page list to choose further reading. Determining how closely a page addresses your topic, how reliable its publisher is, or whether its contents are current requires reviewing that page. Keep the supplier’s numeric scores as supplied rather than assigning your own percentage scale or threshold.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

Results can be on the reference website or another domain. This Tool exposes no domain-exclusion control, so it does not promise a list restricted to other websites.

Find Similar Pages with Exa | BlockRun

Find Similar Pages with Exa | BlockRun

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Scope of the lookup

Connect your AI assistant

Choose a starting page

Review the pages

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Scope of the lookup

Connect your AI assistant

Choose a starting page

Review the pages

Questions about this tool.

Will all results be on other websites?

Does the page list include full article text?