MCP Tools Overview
HG Insights provides a suite of native MCP tools plus TrustRadius product tools that give AI assistants access to company intelligence, contact data, product research, SEC filings, intent signals, government contracting data, data warehouse queries, and AI agent invocation capabilities. The per-tool pages in this section are generated from the live tool registry, so they always match what the server serves.
Data accessed through MCP is licensed for agentic workflows — an AI assistant or agent reasoning over results to answer a question, research an account, or produce a deliverable.
It is not licensed for populating or maintaining a system of record. If you need a deterministic process that writes data into a CRM, MDM, data warehouse, or similar store — on a schedule, per record, or as a scripted batch — use the HG Insights API or the HG SaaS application instead. Contact your account team if you are unsure which surface fits your use case.
Data Coverage at a Glance
The HG Insights data fabric powers the tools below. The headline numbers buyers care about, by data source:
| Source / dataset | Coverage |
|---|---|
| HG firmographic universe | 40M+ companies · 20B+ datapoints across HG datasets |
| HG technographic | 20K+ tracked technologies · 120M+ verified tech installs |
| HG IT Spend | 140+ IT spend categories (hardware, software, services, communications) |
| HG Contextual Intent | 20K+ intent topics · 65M+ B2B intent signals processed weekly |
| Cloud Dynamics (Intricately) | 10M+ domains monitored · hundreds of millions of DNS records · AWS · Azure · GCP |
| HG Contracts (GSI) | Thousands of ICT-outsourced contracts via Global System Integrators |
| Contact data | 210M+ verified contacts · 35M+ companies · 140M+ direct dials and mobile numbers |
| TrustRadius reviews & intent | 12M+ annual B2B technology evaluators |
| SEC filings | 18M+ filings indexed (full-text since 2001) · ~10K active reporting companies |
| U.S. federal awards (USAspending.gov) | $833B+ in FY25 contract awards · coverage since FY2001 |
| U.S. federal opportunities (SAM.gov) | Daily-updated active solicitations |
| HG data warehouse | Billions of rows of technographic, intent, and spend data |
Sources (all verified 2026-05-11):
- HG Insights internal: company/install counts, active SEC filer count, weekly intent signals (Confluence "AI Transformation" page: "65+ million B2B intent signals weekly").
- HG Insights RGI Fabric marketing page: "20 billion market data points", "140 spend categories".
- HG Confluence "RGI Fabric — Aggregated Messaging Report" (April 2026): "20K+ technologies", "20,100+ intent topics".
- HG Insights Contextual Intent launch (BusinessWire, 2021): "120+ million verified tech installs".
- HG Confluence "Intricately Sensor Networks Technical White Paper" (Jan 2026): "Domains Monitored: 10+ million", "DNS Records Tracked: Hundreds of millions".
- TrustRadius public marketing: "more than 12 million annual B2B technology evaluators".
- Contact provider public marketing: 210M+ verified contacts, 35M+ companies covered, 140M+ direct dials and mobile numbers.
- SEC EDGAR Query API docs and full-text search FAQ: 18M+ filings indexed, full-text since 2001.
- USAspending.gov / GovSpend FY25 summary: $833B+ in federal contract awards; custom data going back to FY2001.
- SAM.gov public docs: active notices updated daily.
Per-tool numbers are inlined on each tool's detail page below.
Available tools
The full, always-current tool catalog -- grouped by category and generated from the live tool registry -- lives in the per-version index:
- MCP Tools -- v1 -- every v1 tool, by category, each linking to its full reference page.
get_product_information and get_product_reviews are provided via the TrustRadius Product Data integration -- dynamically composed by the MCP aggregator and only available when that integration is configured.
Common Usage Patterns
Single Company Deep Dive
1. company_firmographic → Get basic company info
2. company_technographic → Analyze tech stack
3. company_fai → Understand departmental usage
4. company_intent → Check buying signals
Market Research
1. get_product_category → Explore categories
2. search_companies → Find companies using specific tech
3. company_spend → Analyze spending patterns
Lead Qualification
1. company_firmographic → Verify company details
2. company_technographic → Check for competitive tech
3. company_intent → Identify buying signals
Product Research (TrustRadius)
1. get_product_information → Get product details, pricing, competitors
2. get_product_reviews → Read customer reviews and ratings
3. company_technographic → See which companies use the product
GSI/Contract Analysis
1. company_contracts → Find ICT outsourced contracts with GSIs
2. company_firmographic → Understand company profile
3. company_spend → See what spend GSI influences
4. company_technographic → Track tech transformations during contract
Note: Contract data covers ICT outsourced contracts, not product-level agreements. For product renewal timing, use technographic first_verified_date as a proxy.
Contact Prospecting
1. contact_search → Find contacts by title/seniority (2 credits)
2. Review results to identify best matches
3. contact_enrich → Get email/phone for selected contacts (0.2/email + 2/phone reveal)
SEC Research
1. sec_full_text_search → Find filings mentioning specific topics
2. sec_filing_section → Extract specific sections for analysis
3. company_firmographic → Get company context
Intent-Based Prospecting
1. intent_category (v1 only) → Find accounts researching your category
2. company_firmographic → Qualify account fit
3. contact_search → Find decision makers
Government Contracting
1. search_gov_opportunities → Find open solicitations by keyword/NAICS
2. search_federal_contracts → Research past awards in the space
3. company_gov_relationships → Map prime/sub partnerships
4. company_gov_opportunities → Find recompetes for a specific contractor
Custom Data Query
1. hg_catalog → Discover available tables, columns, and join keys
2. hg_data_query → Execute custom SQL SELECT queries against the data warehouse
3. company_firmographic → Enrich results with firmographic context
Agent Workflows
1. phoenix_list_agents → See available agents
2. phoenix_invoke_agent → Start agent run with inputs
3. phoenix_get_run_status → Poll for completion
4. Download artifacts from returned URLs
Tool Composition
HG MCP Server tools are designed to work together. Start with broad searches, then drill down into specific companies:
Example workflow:
- Use
search_companiesto find companies in target industry - For each company, call
company_firmographicfor basic details - Use
company_technographicto check tech stack fit - Check
company_intentfor buying signals - Analyze
company_spendto understand budget allocation
Rate Limits
HG Insights enforces a per-minute limit on tool calls, shared across your whole organization:
- 1,000 tool calls per minute per organization. All of your organization's API keys draw on the same window — the limit is per company, not per key. Discovery and protocol methods (
initialize,tools/list,prompts/list,resources/list,ping) are tracked under a separate, more permissive bucket and rarely a constraint in practice. - 20 tool calls per second per organization. A short burst cap on top of the per-minute one, so a clump of calls fired in the same second is rejected even when you are well inside your minute budget. Both windows are checked on every
tools/calland the tighter one wins — a 429 from this cap carries aRetry-Afterof about a second. Spread bulk work out rather than firing it all at once. - Cache hits still count toward the rate limit. Serving a cached response costs zero credits, but it is still a request your pod has to handle, so it consumes rate-limit budget like any other call. Caching lowers your bill, not your throughput ceiling.
Caching & Pricing
Cached tool responses cost zero credits. When multiple users in your organization request the same data, only the first request consumes credits—subsequent requests hit the cache for free.
How cache hits work
All users in your organization share the same cache bucket for a given tool on a given MCP version. This means:
- User A calls
company_firmographicfor company X → pays 0.1 credits (per company returned on v2) - User B in the same org calls the same tool for company X within the cache window → pays 0 credits (cache hit)
The cache key includes the MCP version, so the same logical request issued on v1 and on v2 occupies two separate buckets and is charged twice. If your organization uses both versions, route repeated lookups through one of them to get the benefit.
Cache durations by tool
| Tool | Cache Duration | Use Case |
|---|---|---|
| company_firmographic | 30 days | Industry, size, revenue, HQ, and corporate hierarchy for a known company |
| company_technographic | 30 days | Currently installed tech stack — for trends over time use company_install_time_series |
| company_intent | 30 days | Scored intent topics for one company, plus TrustRadius activity events — for "who is researching X?" use intent_category (v1 only) |
| company_spend | 30 days | Modeled annual IT spend in USD, by category and country |
| company_fai | 30 days | Functional Area Intelligence — which departments use which products |
| company_ai_spend (v2 only) | 30 days | Estimated annual AI spend in USD (software, services, hardware), by category and country |
| company_cloud_spend | 30 days | Which cloud/CDN/hosting vendors a company uses, with adoption dates — no dollar figures despite the name |
| company_contracts | 30 days | ICT outsourced contracts (typically GSI-brokered); optionally federal awards and SAM.gov registration — not product-level renewals |
| company_operating_signals | 30 days | Operating posture rolled up from HG mentions, plus GenAI/AI-maturity signals |
| company_research (v1 only) | 30 days | EXPENSIVE (~10 credits) — full multi-signal profile aggregating several tools above; don't use it for one signal |
| get_product_information | 30 days | TrustRadius product overview, rating, and review counts by product name — not HG's product catalog |
| search_companies | 7 days | Find companies by firmographic/technographic criteria. v1 returns some firmographic columns; v2 returns identity columns only — enrich via company_firmographic |
| contact_search | 7 days | Discover people by title/seniority/location — no email or phone; needs a contact provider |
| contact_enrich | 7 days | Enrich a known person: email, profiles, employment history. Phone reveal costs ~10x an email and its default differs by version — opt-in on v1, on by default on v2 |
| get_product_reviews | 14 days | TrustRadius reviews for a product, with an aggregated pros/cons summary |
| hg_catalog | 1 day | Data-warehouse schema — tables, columns, and join keys (not the product catalog) |
Note on "no data" responses: Some tools flag a "we have no coverage for this company" answer explicitly — today company_intent and company_operating_signals. When they do, the response caches for 6 hours instead of the tool's full TTL, so a backfill on HG's side is picked up within a business day rather than being masked for a month. Tools that return an ordinary empty result without that flag — an unmatched search_companies query, for instance — keep their normal duration.
Longer cache durations mean more opportunities for cache hits: the 30-day tools benefit most from repeated queries across your organization.
Most tools above are available on every MCP version; the ones marked otherwise are not. Note that v2 access is granted per organization — if your org is not entitled to v2, company_ai_spend will not appear in your tools/list, while company_research and intent_category are v1-only in the other direction. Each tool's own reference page — v1 or v2 — states its credit cost, and the table above is the reference for its cache duration.
Not every tool is cached, and the table above is the complete list of those that are. Any tool absent from it is never served from cache. Many of those are free, so it costs you nothing. The paid ones bill on every call, with no cache to fall back on:
- Flat rate — the SEC tools (
sec_filing_section,sec_full_text_search), and the government-contracting tools (search_federal_contracts,search_gov_opportunities,company_gov_opportunities,company_gov_relationships). - Priced per result —
company_ai_maturity(2 credits per company),hg_data_query(per row),company_install_time_series(per product),get_company_hierarchy(per node),intent_category(per 100 categories),product_search_and_enrich(per matched product),web_search(per call), andhg_query(billed through the underlying agent run).
Budget repeat calls to any of these at full price: the deduplication advice below saves you nothing on them. To check a tool not named here, look it up in the table above — if it is absent, it is not cached.
Durations are approximate. Entries expire with about ±10% jitter, so a "30 days" entry may lapse a few days early and the 6-hour negative cache lands between roughly 5½ and 6½ hours. Treat the figures as planning guidance, not guarantees.
Pricing implications
Cache hits reduce your effective cost per query, especially for data-heavy tools like company_technographic (2 credits per company returned on v2). For exact credit costs, see Credit cost per tool below — it is generated from the billing table, so it cannot drift from what you are actually charged. A few tools are listed only on their own reference page rather than in that table; each tool page always states its own rate. The pricing page groups these into plan tiers.
For developers
If you're building a tool or integration on top of HG Insights' MCP API, note that cache keys include organization context but not user identity. This means:
- Queries from different users in the same org hit the same cache
- Design your integration to deduplicate redundant API calls within your organization to maximize cache hit rates
- Avoid calling the same tool with identical parameters multiple times in quick succession when possible
Error Handling
All tools return structured error responses:
{
"error": {
"code": "COMPANY_NOT_FOUND",
"message": "Company not found for domain: example.com",
"details": {}
}
}
Common error codes:
INVALID_PARAMETERS: Tool parameters are invalid or missingCOMPANY_NOT_FOUND: Specified company not found in databaseRATE_LIMIT_EXCEEDED: Rate limit reachedAUTHENTICATION_ERROR: API key invalid or missingINTERNAL_ERROR: Server error (contact support)
Next Steps
- View detailed tool reference (generated from code)
- See example workflows
- Learn about MCP prompts
- Read best practices guide
What are AI Credits?
AI Credits are the unit of metered usage for HG MCP Server tool calls. Every plan includes a monthly credit allotment; usage beyond it is billed at your plan's overage rate. The pricing page lists each plan's included credits and overage rate, and your organization's current usage and remaining balance are shown in the HG Insights app under your organization's billing/usage settings.
How a call is charged:
- Most tools cost a flat number of credits per call — the figure in the table below.
- Some tools bill per result returned. For those, the Basis column states the unit, so a call
returning 50 rows costs 50× the listed figure. Narrow your query (filters, lower
maxResults) to control cost. - A few tools are free (catalog lookups, agent/artifact management) or metered separately
(billed through at the underlying cost). Discovery and protocol methods (
tools/list, etc.) are never charged. - Failed calls are not charged, and cached responses within the cache window do not incur a second charge.
Each tool's own reference page repeats its exact rate in a Credits section, so you never have to leave the page you're on to know what a call costs.
The admin_* tools (user, integration, API-key, and marketplace-submission management) are
admin-scoped operational calls — available only to an admin-scoped API key, and hidden from a
standard tools/list. They are not metered in AI Credits and so do not appear in the table below.
Credit cost per tool
Exact AI Credit cost for the tools listed below, generated from the billing table so it cannot drift from what you are actually charged. The pricing page groups these into tiers; this is the per-tool detail. A few tools are not listed here — admin tools are not metered in AI Credits, and any tool still exclusive to a newer API version carries its rate on its own reference page instead.
Most tools bill a flat rate per call. Some bill per result returned — for those, the Basis
column states the unit, so a call returning 50 rows costs 50x the listed figure. A handful are
metered separately and have no flat per-call rate. On v2, the company data tools
(company_firmographic, company_technographic, company_spend, company_ai_spend,
company_ai_maturity, company_contracts) bill per matched company returned; on v1 they bill the
listed rate once per call.
| Tool | Name | AI Credits | Basis |
|---|---|---|---|
company_ai_maturity | Company AI Maturity | 2 | 2 per company returned |
company_cloud_spend | Company Cloud Spend | 2 | Per call |
company_contracts | Company Contracts | 1 | 1 per company returned |
company_fai | FAI Scores | 2 | Per call |
company_firmographic | Company Firmographics | 0.1 | 0.1 per company returned |
company_gov_opportunities | Company Gov Opportunities | 1 | Per call |
company_gov_relationships | Company Gov Relationships | 1 | Per call |
company_install_time_series | Company Install Time Series | 3 | 3 per product returned |
company_intent | Company Intent | 0.1 | Per call |
company_operating_signals | Company Operating Signals | 2 | Per call |
company_research | Company Research | Metered separately | Sum of the sections returned (~10 for a full profile) |
company_spend | Company Spend | 3 | 3 per company returned |
company_technographic | Company Technographics | 2 | 2 per company returned |
contact_enrich | Contact Enrich | 0.2 / 2 | 0.2 per email reveal, 2 per phone reveal (phone reveal is opt-in on v1, on by default on v2) |
contact_search | Contact Search | 2 | Per call |
customer_data_explore | Customer Data Explore | Free | No credits consumed |
customer_data_query | Customer Data Query | Free | No credits consumed |
get_company_hierarchy | Company Hierarchy | 0.1 | 0.1 per node returned |
get_product_attribute | Get Product Attribute | Free | No credits consumed |
get_product_category | Get Product Category | Free | No credits consumed |
get_product_information | Product Information | 1 | Per call |
get_product_reviews | Product Reviews | 1 | Per call |
get_vendor_information | Vendor Information | Free | No credits consumed |
hg_catalog | HG Data Catalog | Free | No credits consumed |
hg_data_query | HG Data Query | 1 | 1 per row returned |
intent_category | Intent Category | 1 | 1 per 100 categories returned |
list_fai_departments | FAI Departments | Free | No credits consumed |
list_intent_topics | Intent Topics | Free | No credits consumed |
market_data_agent | Market Data Agent | Metered separately | Billed through at cost via the underlying agent run |
phoenix_get_artifact | Get Artifact | Free | No credits consumed |
phoenix_get_run_status | Get Run Status | Free | No credits consumed |
phoenix_invoke_agent | Invoke Agent | Free | No credits consumed |
phoenix_list_agents | List Agents | Free | No credits consumed |
phoenix_list_artifacts | List Artifacts | Free | No credits consumed |
phoenix_onboarding | Guided Onboarding | Free | No credits consumed |
product_search_and_enrich | Product Search & Enrich | 1 | 1 per enriched product returned |
search_companies | Company Search | 1 | 1 per 100 companies returned |
search_federal_contracts | Search Federal Contracts | 1 | Per call |
search_gov_opportunities | Search Gov Opportunities | 1 | Per call |
search_industries_naics_sic | Industry Search (NAICS/SIC) | Free | No credits consumed |
sec_filing_section | SEC Filing Section | 1 | Per call |
sec_full_text_search | SEC Full Text Search | 1 | Per call |
web_search | Web Search | 0.05 / 0.10 | 0.05 per basic search, 0.10 per advanced extraction |