# HSH Data-on-Demand (remote · dod.hshintelligence.com)

Made-to-order data for AI agents: company intel, B2B contacts, scraping. Pay per call via x402.

- Trust score: 62/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `dod.hshintelligence.com`: 62/100 (this document), [markdown](https://verifymcp.io/servers/hshintelligence-data-on-demand/dod.md), [page](https://verifymcp.io/servers/hshintelligence-data-on-demand/dod)

## Channel facts

- Endpoint: `https://dod.hshintelligence.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 32 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4456 tokens (~139/item across 32 items; 32 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 76% of tool parameters carry a description.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http hshintelligence-data-on-demand https://dod.hshintelligence.com/mcp
```

### Codex

```toml
[mcp_servers.hshintelligence-data-on-demand]
url = "https://dod.hshintelligence.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hshintelligence-data-on-demand": {
      "type": "remote",
      "url": "https://dod.hshintelligence.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add hshintelligence-data-on-demand --url https://dod.hshintelligence.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  hshintelligence-data-on-demand:
    url: "https://dod.hshintelligence.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "hshintelligence-data-on-demand": {
      "type": "http",
      "url": "https://dod.hshintelligence.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 60, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 58, +2)

- [security improvement] TLS certificate: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 32 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Stability: unverified → 0.07
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-27 (score 56, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 56)

First indexed and scored.

## MCP tools (32)

### `hsh-company-intelligence` (~114 tokens)

Real-time intelligence on a startup/company by name or domain. Returns: profile, founders, tech stack, hiring signals, YC batch. Supports lookup (1 company) or discover (filtered list). Pay per call via x402 (USDC on Base).

Input parameters:

- `filters` (object): For discover: { industry?, batch?, is_hiring?, has_email? }
- `limit` (number)
- `mode` (string)
- `query` (string, required): Company name or domain, OR a discovery query.

### `hsh-b2b-contact` (~172 tokens)

Verified B2B contact records: name + business email + company. SMTP-validated emails (bounce rate <3%). Industry/title filters. Per-record pricing scales with quantity. Tier 1: 1-50 records ($3-15). Tier 2: 51-5000 records ($15-500). Tier 3: 5001-100K ($250-3000).

Input parameters:

- `industry` (string): Industry filter (e.g., 'D2C skincare', 'B2B SaaS').
- `location` (string): City, state, or country.
- `quantity` (number, required): Number of contacts needed (1-100000).
- `role` (string): Job title or role (e.g., 'CTO', 'Founder', 'Head of Marketing').

### `hsh-b2b-enriched` (~146 tokens)

Multi-source enriched B2B records: name + email + LinkedIn URL + title + company size + industry. Cross-referenced from 3+ sources for accuracy. Tier 1: 1-50 ($3-15). Tier 2: 51-5000 ($15-500). Tier 3: 5001-100K ($250-3000).

Input parameters:

- `company_size` (string): Range like '11-50' or '500+'.
- `industry` (string)
- `quantity` (number, required)
- `role` (string)
- `seniority` (string): Director, VP, C-suite, etc.

### `hsh-b2b-full` (~132 tokens)

Deep enrichment: name + email + phone + LinkedIn + firmographic data + tech stack signals + funding history + revenue estimates. Multi-source fusion (5+ sources). For sales teams that need everything. Tier 2: $15-500 (small batch). Tier 3: $250-3000 (high volume).

Input parameters:

- `funding_stage` (string)
- `industry` (string)
- `quantity` (number, required)
- `revenue_range` (string)
- `tech_stack` (string): Filter by tech they use (e.g., 'Shopify', 'Salesforce').

### `hsh-web-scrape` (~157 tokens)

Custom web scraping: extract structured data from any public site or directory. Handles static HTML, JS-rendered, paginated, and basic anti-bot. Pricing per record + complexity multiplier (1.0-2.5x). Tier 1: $3-15 (50 records). Tier 2: $15-500 (5K records). Tier 3: $250-3000 (100K).

Input parameters:

- `complexity_hint` (string): 'static', 'js_render', 'auth_required'.
- `fields` (string, required): List of fields to extract per record.
- `quantity` (number): Expected record count (or 'all').
- `source_url` (string, required): Target site or section to scrape.

### `hsh-monitoring` (~119 tokens)

Continuous URL/page monitoring with change detection. Daily, hourly, or real-time snapshots. Webhook alerts on diff. Includes screenshot archive. Priced per URL per month ($10/URL/month, 15% off for 6+ month commits).

Input parameters:

- `alert_threshold` (string): 'any_change', 'price_change', 'content_change', 'custom_regex'.
- `duration_months` (number)
- `frequency` (string)
- `urls` (string, required): List of URLs to monitor.
- `webhook_url` (string)

### `hsh-custom-dataset` (~128 tokens)

Novel datasets that don't exist anywhere yet: cross-domain fusion, industry-specific schemas, real-time aggregated intelligence. Setup fee $500 + per-record $0.20. Includes parser dev, QA, and documentation. Tier 3 ($250-3000) for small custom builds, Tier 4 (human-scoped) for novel/large.

Input parameters:

- `delivery_format` (string)
- `quantity_estimate` (number)
- `schema_description` (string, required): Plain English description of what data + structure you need.
- `sources_hint` (string): Suggested data sources if known.

### `hsh-finetune-dataset` (~323 tokens)

Made-to-order, answer-verified datasets for LLM fine-tuning. Describe the task (e.g. 'step-by-step math reasoning', 'SQL generation', 'instruction-following for support replies') and we deliver a clean, HuggingFace-ready dataset in Alpaca schema (instruction/input/output), deduplicated, train/val/test split, with every checkable answer verified in code. Drop the repo straight into Gradients (SN56), TRL, Axolotl, or Unsloth. Verified sample live: huggingface.co/datasets/HSH-Intelligence/verified-math-reasoning-3k. Tier S: 1-2K rows ($75). Tier M: 2-5K rows ($150). Tier L: 5-10K rows ($300). Custom/larger scoped on request.

Input parameters:

- `domain` (string): Subject domain (e.g. 'math', 'SQL', 'customer support', 'legal Q&A').
- `row_count` (number, required): Number of training rows needed (1000-10000 standard; larger scoped on request).
- `schema_hint` (string): Preferred schema. Default: Alpaca instruction/input/output (Gradients-ready).
- `target_platform` (string): Where you'll train — tunes the delivered format.
- `task_description` (string, required): Plain English: what the model should learn to do (the instruction-following task).
- `verification` (string): How answers are checked. Programmatic (code-verified ground truth) where the task allows.

### `hsh-crypto-intel` (~170 tokens)

Complete crypto intel for trading agents. Three layers in one call: (1) cross-exchange POSITIONING — Binance + Bybit funding, open interest, price fused into a signal (overheated-long/short, cross-exchange dislocation); (2) ON-CHAIN whale activity — large confirmed BTC transactions from the latest block; (3) LIQUIDATION RISK — a derived forward-looking cascade-risk score from funding + OI + price. Pay per call via x402 (USDC on Base). Supported assets: BTC, ETH, SOL, BNB, XRP, DOGE.

Input parameters:

- `asset` (string): Asset ticker e.g. BTC, ETH, SOL (default BTC).
- `symbol` (string): Optional explicit perp symbol e.g. BTCUSDT.

### `hsh-india-announcements` (~128 tokens)

Live NSE corporate-announcement intel for Indian listed companies. Each announcement is classified by event type (dividend, earnings, board_meeting, M&A, fundraise, order_win, buyback, investor_meet, management_change, credit_rating) and tagged with sentiment + a plain-English impact summary. Optional symbol filter. Real-time, structured, agent-ready. Pay per call via x402 (USDC on Base).

Input parameters:

- `limit` (number): How many recent announcements.
- `symbol` (string): Optional NSE symbol filter e.g. RELIANCE, TCS.

### `hsh-india-fundamentals` (~191 tokens)

Indian listed-company fundamentals from NSE official XBRL filings — primary regulatory disclosures, no third-party data. Quarterly P&L (revenue, net profit, EPS, net margin) with YoY and QoQ growth, PLUS the annual balance sheet (assets, equity, debt, current assets/liabilities, cash) and self-computed institutional ratios: ROE, ROCE, debt/equity, current ratio, interest coverage, asset turnover. PLUS shareholding pattern (promoter %, public %, promoter-pledge governance flag). Institutional-method (ratios derived from primary filings). Values in INR crore. Pass an NSE symbol. Pay per call via x402 (USDC on Base).

Input parameters:

- `period` (string): Quarterly or Annual.
- `symbol` (string, required): NSE symbol, e.g. RELIANCE, TCS, INFY, HDFCBANK.

### `hsh-mena-intel` (~308 tokens)

MENA (Gulf) market intelligence for trading agents. Combines the signals that actually drive Gulf markets: OIL (Brent + WTI, latest price + 30-day trend + derived Gulf-equity impact — oil is the dominant Gulf market driver), SOVEREIGN MACRO (GDP growth, inflation, GDP size per country from World Bank), USD-PEG stability (Gulf currencies are USD-pegged — a key FX-risk signal), and live MENA EQUITY pricing (price + 52-week positioning for major Gulf stocks like Aramco, Emaar, QNB, Al Rajhi). For SAUDI specifically, adds official Tadawul market data via the SAHMK API: TASI index level, market breadth (advancers/decliners), market mood, and rich per-stock quotes (OHLC, bid/ask, volume). Note: deep Gulf company financials are license-walled (no SEC/NSE-style free disclosure); this delivers the genuinely-free market-level intel. Pass a country code and optional Gulf ticker. Pay per call via x402 (USDC on Base).

Input parameters:

- `country` (string): Gulf country code: SA, AE, QA, KW, BH, OM, EG.
- `ticker` (string): Optional Gulf equity ticker, e.g. 2222.SR (Aramco), EMAAR.AE, QNBK.QA, 1120.SR (Al Rajhi).

### `hsh-esg-events` (~182 tokens)

Authoritative company-attributed ESG material-event intel for US-listed companies. Sourced from SEC EDGAR 8-K + SD filings (companies disclosing their own material events): governance changes, restatements, auditor changes, bankruptcy/debt triggers, material impairments, litigation/other-material-events, conflict-minerals disclosures. Each event is mapped to ESG pillar (E/S/G), severity-graded (1-5), and links to the actual SEC filing. Optional ticker or pillar filter. Pay per call via x402 (USDC on Base).

Input parameters:

- `days` (number): Lookback window in days.
- `limit` (number): Max events to return.
- `pillar` (string): Filter by pillar: E, S, or G.
- `ticker` (string): Filter to one company e.g. AAPL, XOM.

### `hsh-hiring-signal` (~323 tokens)

Multi-signal alt-data intel for investment research. Combines up to six independent free signals into one call: (1) HIRING posture across Greenhouse + Lever + Ashby job boards (gtm_expansion / product_build / balanced_growth / hiring_freeze from department mix); (2) INSIDER activity from SEC Form 4 filings (last 90 days); (3) GITHUB engineering velocity (stars, push recency); (4) WIKIPEDIA public-interest trend; (5) APP STORE top-free ranking presence; (6) HACKER NEWS mention velocity. Operational/behavioral signals that precede price moves. Pass whichever identifiers you have. Pay per call via x402 (USDC on Base).

Input parameters:

- `ashby` (string): Ashby slug (e.g. ramp).
- `company` (string, required): Company display name.
- `github` (string): GitHub owner/repo for engineering-velocity signal (e.g. stripe/stripe-node).
- `greenhouse` (string): Greenhouse board token (e.g. stripe, coinbase).
- `hn` (string): Hacker News search term for buzz signal.
- `ios_app` (string): iOS app name to check top-free ranking (e.g. Cash App).
- `lever` (string): Lever slug (e.g. spotify).
- `ticker` (string): Stock ticker for SEC insider signal (e.g. COIN, AAPL).
- `wiki` (string): Wikipedia article title for interest signal (e.g. Coinbase).

### `hsh-shariah-screen` (~149 tokens)

Rule-based Shariah (Islamic finance) compliance screen for US-listed companies. Applies AAOIFI-style screening using authoritative SEC financials: (1) business-activity screen (flags alcohol, tobacco, gambling, conventional banking/insurance, pork, weapons, adult), (2) financial ratio screens (debt/assets <33%, liquid+interest/assets <33%, receivables/assets <49%). Returns verdict (compliant / non_compliant / questionable) with the exact failing test and ratios. Pay per call via x402 (USDC on Base).

Input parameters:

- `ticker` (string, required): US-listed ticker to screen, e.g. AAPL, XOM, JPM.

### `hsh-esg-news` (~182 tokens)

EU & global ESG controversy intel for compliance and trading agents. Detects company ESG controversies (environmental, social, governance) from worldwide news in real time, then enriches each with GLEIF entity resolution (LEI + country of domicile) and EU sanctions-list screening. Pillar-classified, severity-graded, source-linked. Pass region='EU' to filter to EU-domiciled companies. News-derived breadth (complements the authoritative SEC-filing ESG product hsh-esg-events). Pay per call via x402 (USDC on Base).

Input parameters:

- `company` (string): Optional company-name filter.
- `limit` (number): Max controversies to return.
- `pillar` (string): Filter by pillar: E, S, or G.
- `region` (string): Pass 'EU' to filter to EU-domiciled companies.

### `hsh-cricket-fantasy-picks` (~110 tokens)

Fantasy cricket picks + captain for a T20 match. Ranks players by predicted fantasy value and names the optimal captain (35.6% captain-hit, 2x random). Dream11-style. Pay per call via x402.

Input parameters:

- `is_chase` (number): 1 if this team is chasing, else 0.
- `players` (string, required): List of player names in the match squad.
- `venue` (string): Optional venue name for pitch context.

### `hsh-cricket-chase-winprob` (~128 tokens)

Real-time chase win-probability for a T20 run chase, updated per ball. Model AUC 0.88, beats run-rate heuristic by 8.6pts. In-play betting signal. Pay per call via x402.

Input parameters:

- `balls_bowled` (number, required): Legal balls bowled in the chase (0-120).
- `cum_runs` (number, required): Runs scored so far.
- `target` (number, required): Target to win (1st innings total + 1).
- `wickets` (number, required): Wickets lost (0-10).

### `hsh-cricket-momentum` (~103 tokens)

Momentum & pressure index for a live T20 chase — quantifies which side is gaining (the swing signal) plus a pressure score. In-play trader signal. Pay per call via x402.

Input parameters:

- `curr` (object, required): Current state {balls_bowled, wickets, cum_runs, target}.
- `prev` (object, required): Prior state {balls_bowled, wickets, cum_runs, target}.
- `target` (number, required): Target to win.

### `hsh-cricket-parscore` (~94 tokens)

Par-score / projected first-innings total from any mid-innings state. Accurate to +/-8.6 runs in death overs, beats naive extrapolation by 10.6 runs. Over/under betting signal. Pay per call via x402.

Input parameters:

- `balls_bowled` (number, required)
- `cum_runs` (number, required)
- `venue` (string)
- `wickets` (number, required)

### `hsh-cricket-timeline` (~75 tokens)

Over-by-over win-probability timeline (the broadcast 'worm') for a full T20 chase. Media/broadcast-grade. Pay per call via x402.

Input parameters:

- `events` (string, required): Per-over states [{balls_bowled, wickets, cum_runs, target}].
- `target` (number, required)

### `hsh-cricket-matchup` (~81 tokens)

Batter-vs-bowler head-to-head record (111K pairs, Bayesian-adjusted): balls, runs, dismissals, dominance score. Fantasy + in-play edge. Pay per call via x402.

Input parameters:

- `batter` (string, required): Batter name (partial match ok).
- `bowler` (string, required): Bowler name (partial match ok).

### `hsh-cricket-first-winprob` (~99 tokens)

First-innings win-probability while a team is still setting a total (AUC 0.76, uses venue + team strength). Pay per call via x402.

Input parameters:

- `balls_bowled` (number, required)
- `chase_elo` (number)
- `cum_runs` (number, required)
- `set_elo` (number)
- `venue` (string)
- `wickets` (number, required)

### `hsh-cricket-form` (~56 tokens)

Player form & fatigue rating (hot/cold form + bowling-workload fatigue flag) for established IPL players. Fantasy signal. Pay per call via x402.

Input parameters:

- `player` (string, required): Player name (partial match ok).

### `hsh-cricket-chase-difficulty` (~59 tokens)

Chase difficulty rating at the innings break — grades how hard a target is (Easy to Very Hard) from historical chase-success data. Pay per call via x402.

Input parameters:

- `target` (number, required): The target to be chased.

### `hsh_describe_data_need` (~143 tokens)

FREE. Describe any data need in plain language and receive an instant firm quote from HSH Intelligence Data-on-Demand: price in USDC, scope, a frozen quote_ref, and a pay_url. Pay the quote via x402 (USDC on Base or Solana) at the pay_url to place the order; delivery in 24h. Use this BEFORE purchasing custom data.

Input parameters:

- `budget_usd` (number): Optional budget in USD; we may accept it within our floor.
- `need` (string, required): Free-text description of the data you need (type, volume, geography, freshness).
- `urgency` (string): Optional urgency.

### `hsh_list_capabilities` (~33 tokens)

FREE. List HSH Intelligence's catalogued data capabilities with live pricing, plus how to order custom data.

### `hsh_check_quote` (~68 tokens)

FREE. Check a quote_ref from hsh_describe_data_need: status, frozen price, expiry, and pay_url if still payable.

Input parameters:

- `quote_ref` (string, required): The quote reference, e.g. HSHQ-A1B2C3D4E5F6

### `hsh_subscribe_data_feed` (~224 tokens)

FREE. Register a STANDING subscription so HSH watches for events matching your interest (e.g. SEC filings by form type and/or ticker/sector keywords) and sends you a quote the moment a match is caught. Turns one-off data buying into an always-on feed. Pay per matched delivery via x402.

Input parameters:

- `agent_id` (string): Optional agent/wallet id to associate with this subscription.
- `callback_url` (string): Optional webhook URL to receive match notifications; omit to poll with hsh_check_subscription.
- `forms` (array): Optional SEC form types to match, e.g. ["8-K","10-Q"]. Omit to match any material form.
- `keywords` (array): Optional tickers/company names/sector terms to match in the filing.
- `max_price_usd` (number): Optional max price per matched delivery; quotes above this are skipped.
- `need` (string): Plain-language description of what to watch (e.g. 'any 8-K or 10-Q mentioning AAPL or semiconductors').

### `hsh_check_subscription` (~65 tokens)

FREE. Check a subscription by its sub_ref (HSHSUB-XXXXXXXXXX): what it's watching, status, and match criteria.

Input parameters:

- `sub_ref` (string, required): The subscription reference, e.g. HSHSUB-A1B2C3D4E5

### `hsh_broker_data_request` (~139 tokens)

Route a data need through HSH (the data-fulfillment layer for agents). HSH checks its warm inventory first — if a matching product is pre-positioned, you get an immediate-fulfillment quote; otherwise a fresh-fulfillment quote. Use this when you need data mid-task and want HSH to fulfill it.

Input parameters:

- `agent_id` (string): Optional calling-agent identifier
- `keywords` (array): Optional match keywords (e.g. tickers, topics)
- `max_price_usd` (number): Optional budget ceiling in USD
- `need` (string, required): Plain-language description of the data you need

### `hsh_check_order` (~55 tokens)

FREE. Check fulfillment status of a paid order by its order reference (HSH-XXXXXXXX).

Input parameters:

- `order_ref` (string, required): The order reference, e.g. HSH-1A2B3C4D

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/hshintelligence-data-on-demand/dod#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 61
- 2026-08-01: 61
- 2026-07-31: 60
- 2026-07-30: 59
- 2026-07-29: 58
- 2026-07-28: 58
- 2026-07-27: 56
- 2026-07-26: 56

## Links

- Remote endpoint: https://dod.hshintelligence.com/mcp
- Repository: https://github.com/hshintelligence/data-on-demand
- Website: https://dod.hshintelligence.com/
- Changelog RSS feed: https://verifymcp.io/servers/hshintelligence-data-on-demand/dod/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/hshintelligence-data-on-demand/dod/changelog.json
- HTML version of this page: https://verifymcp.io/servers/hshintelligence-data-on-demand/dod