Glasser

Provided by Exa

Deep Neural Retrieval by Meaning

$0.013201 per callanswers within 40s

Multi-step neural retrieval via Exa's deep mode: the request is expanded into several passes over the page index and the strongest pages are returned, each with title, link, published date and author. Up to five extra query variations, the same category, domain and date filters, and text or highlights per hit. One request per call, up to 10 pages; slower and dearer than the standard mode.

How to run it

Step 1Set up

Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.

Set up
set up https://glasser.ai/SKILL.md

Show me how to use the Exa endpoint /search?type=deep on Glasser.

Step 2Try a specific example task

When you need to research a question, you might search for relevant sources and review which results are worth reading more closely.

Copy this prompt into your agent to find sources for your research question.

Prompt
Use exa:/search?type=deep on Glasser.
Search for sources about my research question and explain which returned results are relevant.

Endpoint structure

json
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1
    },
    "category": {
      "enum": [
        "company",
        "publication",
        "news",
        "personal site",
        "financial report",
        "people"
      ],
      "type": "string"
    },
    "contents": {
      "type": "object",
      "properties": {
        "text": {
          "type": "object",
          "properties": {
            "maxCharacters": {
              "type": "integer",
              "maximum": 10000,
              "minimum": 1
            }
          },
          "additionalProperties": false
        },
        "highlights": {
          "type": "object",
          "properties": {
            "query": {
              "type": "string",
              "maxLength": 500,
              "minLength": 1
            },
            "maxCharacters": {
              "type": "integer",
              "maximum": 10000,
              "minimum": 1
            }
          },
          "additionalProperties": false
        }
      },
      "additionalProperties": false
    },
    "numResults": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1
    },
    "excludeDomains": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^(?=.*\\.)(\\*\\.)?[a-z0-9-]+(\\.[a-z0-9-]+)*(\\/[^\\s]*)?$",
        "maxLength": 253,
        "minLength": 4
      },
      "maxItems": 50,
      "minItems": 1
    },
    "includeDomains": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^(?=.*\\.)(\\*\\.)?[a-z0-9-]+(\\.[a-z0-9-]+)*(\\/[^\\s]*)?$",
        "maxLength": 253,
        "minLength": 4
      },
      "maxItems": 50,
      "minItems": 1
    },
    "endPublishedDate": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(\\.\\d{1,3})?Z$"
    },
    "additionalQueries": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 300,
        "minLength": 1
      },
      "maxItems": 5,
      "minItems": 1
    },
    "startPublishedDate": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(\\.\\d{1,3})?Z$"
    }
  },
  "additionalProperties": false
}

How pricing works

Data returnedCharged only when data is returned.$0.013201
Provider errorThe Provider failed to answer.$0.00
Timed outThe Run exceeded its time limit.$0.00
Internal failureAn internal error prevented completion.$0.00
Method POSTVersion 1Provider documentation ↗