Skip to main content
Glama

What agents are asking for

what_agents_are_asking_for
Read-onlyIdempotent

What agents searched this directory for, for deciding which x402 service to build or list. Terms ranked by how many distinct days they were asked, each with catalogue_top: the listings our own search already returns for it. A term being asked does not mean nothing serves it. The window ends a week behind live while the paid tier is on sale (a day when it is not; delay_hours and window_ends_at in the response say which); test traffic, sellers searching their own listings and identifying terms are excluded; floor: a term appears once at least 1 distinct non-seller client IP asked it (read_first in the reply says how to read it). Client counts are IP ceilings, never buyer counts. Paged: limit (default 25), offset, next_offset. Current window grouped by meaning: GET https://api.nohumans.directory/v1/demand/clusters ($0.25 USDC on Base via x402). Free, read-only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoTerms per page, in rank order.
offsetNoWhere to start; each reply gives next_offset.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNo
pageNo
top_needsYes
read_firstNo
delay_hoursYes
terms_totalNo
window_daysYes
total_queriesYes
window_ends_atNo
k_anonymity_unitNo
k_anonymity_floorNo
scripted_rotationNo
distinct_client_ipsNo
top_category_filtersNo
named_listing_lookupsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed21 schema fields changed
    • changedInput schema / properties / limit / default
      Previous value: -100New value: +25
    • changedInput schema / properties / limit / description
      Previous value: -"Terms per reply, in rank order (default 100)."New value: +"Terms per page, in rank order."
    • changedInput schema / properties / offset / description
      Previous value: -"Where to start in the ranked list; each reply says next_offset."New value: +"Where to start; each reply gives next_offset."
    • removedOutput schema / properties / delay_hours / description
      Removed value: -"How far behind live the window ends."
    • removedOutput schema / properties / distinct_client_ips / description
      Removed value: -"A ceiling on independent demand, never a count of buyers."
    • removedOutput schema / properties / k_anonymity_floor / description
      Removed value: -"Distinct non-seller client IPs a term needs before it is reported at all."
    • removedOutput schema / properties / named_listing_lookups / description
      Removed value: -"Searches for one listed service by its own name, asked almost only by clients that searched nothing else: listed apart, same fields as top_needs, not demand. Rule in named_listing_lookup_rule."
    • removedOutput schema / properties / note / description
      Removed value: -"The exclusions, stated in words."
    • removedOutput schema / properties / page / description
      Removed value: -"offset, limit, returned, terms_total, next_offset (null on the last page)."
    • removedOutput schema / properties / read_first / description
      Removed value: -"How to read this feed, in a few lines. Read before the data."
    • removedOutput schema / properties / scripted_rotation / description
      Removed value: -"Terms asked by many client IPs almost all of which searched only once in the whole window (one caller on rotating addresses): listed apart, same fields as top_needs plus share_single_search_client_ips, not demand. Rule in scripted_rotation_rule."
    • removedOutput schema / properties / terms_total / description
      Removed value: -"How many terms the window publishes; top_needs holds one page of them."
    • removedOutput schema / properties / top_needs / description
      Removed value: -"Terms ranked by how many distinct days they were asked."
    • removedOutput schema / properties / top_needs / items / properties / buyer_client_ips / description
      Removed value: -"Distinct non-seller client IPs; a ceiling on independent askers, never a count of buyers."
    • removedOutput schema / properties / top_needs / items / properties / catalogue_status / description
      Removed value: -"not_checked_yet means NOT searched yet, not that nothing exists."
    • removedOutput schema / properties / top_needs / items / properties / catalogue_top / description
      Removed value: -"The three listings this directory's own search returned for the term (id, name, status, price_amount), searched at catalogue_checked_at_iso. Null only when catalogue_status is not_checked_yet."
    • removedOutput schema / properties / top_needs / items / properties / distinct_days / description
      Removed value: -"UTC calendar dates on which non-sellers asked it."
    • removedOutput schema / properties / top_needs / items / properties / self_monitoring_searches / description
      Removed value: -"Of `searches`, how many came from clients that also edit listings here."
    • removedOutput schema / properties / total_queries / description
      Removed value: -"Every search in the window, before exclusions."
    • removedOutput schema / properties / window_days / description
      Removed value: -"Length of the reported window."
    • removedOutput schema / properties / window_ends_at / description
      Removed value: -"Unix seconds at which the window closes."
  2. Changed1 schema field changed
    • addedOutput schema / properties / scripted_rotation
      Added value: +{
      +  "description": "Terms asked by many client IPs almost all of which searched only once in the whole window (one caller on rotating addresses): listed apart, same fields as top_needs plus share_single_search_client_ips, not demand. Rule in scripted_rotation_rule.",
      +  "items": {
      +    "additionalProperties": true,
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  3. Changed4 schema fields changed
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 100,
      +  "description": "Terms per reply, in rank order (default 100).",
      +  "maximum": 1000,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "description": "Where to start in the ranked list; each reply says next_offset.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / page
      Added value: +{
      +  "description": "offset, limit, returned, terms_total, next_offset (null on the last page).",
      +  "type": "object"
      +}
    • addedOutput schema / properties / terms_total
      Added value: +{
      +  "description": "How many terms the window publishes; top_needs holds one page of them.",
      +  "type": "integer"
      +}
  4. Changed1 schema field changed
    • addedOutput schema / properties / named_listing_lookups
      Added value: +{
      +  "description": "Searches for one listed service by its own name, asked almost only by clients that searched nothing else: listed apart, same fields as top_needs, not demand. Rule in named_listing_lookup_rule.",
      +  "items": {
      +    "additionalProperties": true,
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  5. Changed2 schema fields changed
    • addedOutput schema / properties / top_needs / items / properties / catalogue_status
      Added value: +{
      +  "description": "not_checked_yet means NOT searched yet, not that nothing exists.",
      +  "enum": [
      +    "checked",
      +    "search_returned_nothing",
      +    "not_checked_yet"
      +  ],
      +  "type": "string"
      +}
    • changedOutput schema / properties / top_needs / items / properties / catalogue_top / description
      Previous value: -"The three listings this directory's own search returns for the term right now (id, name, status, price_amount). Null beyond the first terms checked: search it yourself."New value: +"The three listings this directory's own search returned for the term (id, name, status, price_amount), searched at catalogue_checked_at_iso. Null only when catalogue_status is not_checked_yet."
  6. Changed5 schema fields changed
    • changedOutput schema / properties / read_first / description
      Previous value: -"How to read this feed, in three lines. Read before the data."New value: +"How to read this feed, in a few lines. Read before the data."
    • addedOutput schema / properties / top_needs / items / properties / buyer_client_ips
      Added value: +{
      +  "description": "Distinct non-seller client IPs; a ceiling on independent askers, never a count of buyers.",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / top_needs / items / properties / catalogue_top
      Added value: +{
      +  "description": "The three listings this directory's own search returns for the term right now (id, name, status, price_amount). Null beyond the first terms checked: search it yourself.",
      +  "items": {
      +    "additionalProperties": true,
      +    "type": "object"
      +  },
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
    • removedOutput schema / properties / top_needs / items / properties / days_asked
      Removed value: -{
      -  "type": "integer"
      -}
    • addedOutput schema / properties / top_needs / items / properties / distinct_days
      Added value: +{
      +  "description": "UTC calendar dates on which non-sellers asked it.",
      +  "type": "integer"
      +}
  7. Changed1 schema field changed
    • addedOutput schema / properties / read_first
      Added value: +{
      +  "description": "How to read this feed, in three lines. Read before the data.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  8. Changed2 schema fields changed
    • removedOutput schema / properties / needs_not_yet_persistent
      Removed value: -{
      -  "description": "Terms asked on a single day so far: same fields and same exclusions as top_needs, published unranked rather than dropped. On a window still filling these are usually the descriptive needs, because a persistence rule selects for monitors that poll daily. Read both arrays to see the whole market.",
      -  "items": {
      -    "additionalProperties": true,
      -    "properties": {
      -      "clients": {
      -        "type": "integer"
      -      },
      -      "days_asked": {
      -        "type": "integer"
      -      },
      -      "q": {
      -        "type": "string"
      -      },
      -      "searches": {
      -        "type": "integer"
      -      },
      -      "self_monitoring_searches": {
      -        "description": "Of `searches`, how many came from clients that also edit listings here.",
      -        "type": "integer"
      -      }
      -    },
      -    "required": [
      -      "q"
      -    ],
      -    "type": "object"
      -  },
      -  "type": "array"
      -}
    • changedOutput schema / properties / top_needs / description
      Previous value: -"Terms asked on two or more distinct days, ranked by that count. Persistence, not volume: a burst occupies one day and cannot rank."New value: +"Terms ranked by how many distinct days they were asked."
  9. Changed2 schema fields changed
    • addedOutput schema / properties / needs_not_yet_persistent
      Added value: +{
      +  "description": "Terms asked on a single day so far: same fields and same exclusions as top_needs, published unranked rather than dropped. On a window still filling these are usually the descriptive needs, because a persistence rule selects for monitors that poll daily. Read both arrays to see the whole market.",
      +  "items": {
      +    "additionalProperties": true,
      +    "properties": {
      +      "clients": {
      +        "type": "integer"
      +      },
      +      "days_asked": {
      +        "type": "integer"
      +      },
      +      "q": {
      +        "type": "string"
      +      },
      +      "searches": {
      +        "type": "integer"
      +      },
      +      "self_monitoring_searches": {
      +        "description": "Of `searches`, how many came from clients that also edit listings here.",
      +        "type": "integer"
      +      }
      +    },
      +    "required": [
      +      "q"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / top_needs / description
      Previous value: -"Terms ranked by how many distinct days they were asked."New value: +"Terms asked on two or more distinct days, ranked by that count. Persistence, not volume: a burst occupies one day and cannot rank."
  10. Changed1 schema field changed
    • removedOutput schema / properties / top_lookups
      Removed value: -{
      -  "description": "Endpoint URLs agents asked us to resolve.",
      -  "items": {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  "type": "array"
      -}
  11. Changed2 schema fields changed
    • removedOutput schema / properties / top_zero_result_terms
      Removed value: -{
      -  "description": "What agents searched for and found nothing — the gaps in this market.",
      -  "items": {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  "type": "array"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "window_days",
      -  "delay_hours",
      -  "total_queries",
      -  "top_needs",
      -  "top_zero_result_terms"
      -]New value: +[
      +  "window_days",
      +  "delay_hours",
      +  "total_queries",
      +  "top_needs"
      +]
  12. Added

TDQS

Score is being calculated.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.