Hyperresearch Answers

Ask a research question, answered from quoted sources

ask

Answers a research question from the live web plus 90+ structured public data sources, including SEC EDGAR company filings, FDIC bank data, FEC campaign-finance and lobbying disclosures, USPTO patents and trademarks, FRED and Census economic series, ClinicalTrials.gov and openFDA, NOAA weather and climate records, scholarly databases and books, market data and posts on X: a short answer checked word for word against quoted sources with their URLs, or an honest not-found. Suited to market size and growth, competitors, company facts, pricing, statistics, regulations and recent events. Ask in plain language, one question per call; split a broad brief into several asks. Prices: fast 5¢ · standard 10¢, 20¢ if it has to dig deeper · max 50¢; an honest not-found costs 20% to 100% of the call's price (up to 20¢ for a standard ask that digs deeper). A standard ask needs 20¢ available unless max_cost_cents is below 20. A paywalled article the call reads may add a surcharge of 1.5 times the article's licence cost (licence price plus transaction fee), rounded up to the cent. Hard questions can take 1-5 minutes. If the result says pending, call get_answer with the id; you will not be charged twice. Each call is charged to the user's prepaid Hyperresearch Answers balance.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "question": "<question>"
    },
    "name": "ask"
  }
}

Input Schema

Name	Required	Description	Default
`mode`	No	How hard to look: fast (5¢, no escalation, about 45 s), standard (10¢, 20¢ if it has to dig deeper; the default, up to about 3 min) or max (50¢, numbers confirmed on two sites, up to about 5 min). `deep` is accepted as the old name for max.	standard
`question`	Yes	One factual question, asked the way you would ask a researcher.
`exclude_text`	No	Short phrases that must not appear in the returned text.
`include_text`	No	Short phrases that must all appear in the returned text.
`max_cost_cents`	No	The most this call may cost, in cents. Below the mode price the call is refused. For standard, below 20 it never digs deeper and costs at most 10¢.
`exclude_domains`	No	Never sources on these domains (or subdomains).
`include_domains`	No	Only sources on these domains (and subdomains), e.g. ["sec.gov"].
`end_published_date`	No	Only sources published on or before this ISO date (YYYY-MM-DD). Undated sources are left out when a date is set.
`start_published_date`	No	Only sources published on or after this ISO date (YYYY-MM-DD). Undated sources are left out when a date is set.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 5, 2026

addedInput schema / properties / end_published_date

Added value: +{
+  "description": "Only sources published on or before this ISO date (YYYY-MM-DD). Undated sources are left out when a date is set.",
+  "maxLength": 40,
+  "type": "string"
+}

addedInput schema / properties / exclude_domains

Added value: +{
+  "description": "Never sources on these domains (or subdomains).",
+  "items": {
+    "maxLength": 253,
+    "type": "string"
+  },
+  "maxItems": 50,
+  "type": "array"
+}

addedInput schema / properties / exclude_text

Added value: +{
+  "description": "Short phrases that must not appear in the returned text.",
+  "items": {
+    "maxLength": 100,
+    "type": "string"
+  },
+  "maxItems": 5,
+  "type": "array"
+}

addedInput schema / properties / include_domains

Added value: +{
+  "description": "Only sources on these domains (and subdomains), e.g. [\"sec.gov\"].",
+  "items": {
+    "maxLength": 253,
+    "type": "string"
+  },
+  "maxItems": 50,
+  "type": "array"
+}

addedInput schema / properties / include_text

Added value: +{
+  "description": "Short phrases that must all appear in the returned text.",
+  "items": {
+    "maxLength": 100,
+    "type": "string"
+  },
+  "maxItems": 5,
+  "type": "array"
+}

addedInput schema / properties / start_published_date

Added value: +{
+  "description": "Only sources published on or after this ISO date (YYYY-MM-DD). Undated sources are left out when a date is set.",
+  "maxLength": 40,
+  "type": "string"
+}

First observedOct 31, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Far exceeds the annotations: discloses per-mode pricing, a hard cost ceiling, the fact that an honest not-found still costs 20%–100% of the price, a 1.5x surcharge for paywalled articles, a 20¢ balance requirement for standard asks, and 1–5 minute latency. It also explains the pending/get_answer handoff with an explicit no-double-charge guarantee, which is exactly the async behavior an agent needs to plan around.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and source coverage are correctly front-loaded, but the long dataset enumeration and the pricing passage are dense and partially repeat the mode parameter's own price table. The single unbroken paragraph makes cost rules harder to scan than they need to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden itself and does so: quoted-and-checked short answer with URLs, honest not-found, and a pending state resolvable via get_answer. Combined with pricing, latency, and surcharge disclosure, an agent can decide, budget, and handle the response without further information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter is already documented, including the mode enum, domain filters, and max_cost_cents behavior. The description adds only marginally — reinforcing one-question-per-call and the 20¢ availability rule — so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — answers a research question — and immediately bounds the source universe (live web plus named structured datasets like SEC EDGAR, FDIC, FEC, USPTO, FRED, openFDA). It also names the output contract (quoted, URL-cited answer or an honest not-found), so an agent knows exactly what it will get back.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit use cases (market size and growth, competitors, company facts, pricing, statistics, regulations, recent events) and explicit input discipline (plain language, one question per call, split broad briefs into several asks). It also routes the agent to get_answer when a result is pending. The gap is the `search` sibling: nothing says when to use this paid ask versus doing a plain search first.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Hyperresearch Answers tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.