Harcourt Valuations — AI & Agent Reference

Service Overview

Harcourt Valuations produces institutional-grade Net Asset Value (NAV) reports for mining companies. Each report contains a full discounted cash flow (DCF) model for every mine or project owned by the company, a P/NAV ratio, and a two-way sensitivity table showing how NAV per share moves with metal prices and discount rates.

The core thesis: the answer is a number. Mining equity analysis should produce a specific, defensible per-share value — not a narrative. P/NAV (price to net asset value) is the primary metric used by mining-focused fund managers and sell-side analysts at major Canadian and Australian banks.

Two product tiers

• PDF Report — $15 USD TDN: Full institutional NAV model delivered as an instant PDF download. Payment via Qatom micropay embed or Qatom MCP tool.
• NAV Query API — $1 USD TDN per call: Returns NAV per share at a caller-specified commodity price and discount rate. Ideal for autonomous agents performing portfolio screening or valuation sensitivity analysis at scale. Powered by precomputed DCF sensitivity matrices with bilinear interpolation — no live model re-execution, sub-50ms response. Accessible via Qatom MCP Tool 77 (harcourt_nav_query_api).

Free access

• Klondike Mike chat agent: Free NAV preview at harcourtvaluations.ai and at POST https://reports.harcourtvaluations.ai/chat. Powered by Claude Haiku. Returns current P/NAV, NAV/share, and key catalyst for any covered ticker. Does not require payment.
• Sample report: Full institutional PDF at reports.harcourtvaluations.ai/sample — free, no payment required.
• Live catalog: GET https://reports.harcourtvaluations.ai/catalog returns all covered companies in JSON with metadata.

Covered Companies

Coverage expands as models are completed. This table is maintained by hand and can lag; the catalog endpoint is generated from the live data and is authoritative. Fetch it for the current list:

GET https://reports.harcourtvaluations.ai/catalog
Accept: application/json

NAV Query API

The NAV Query API returns a modelled NAV per share at caller-specified inputs. It does not re-run any live model. Instead, it reads a precomputed sensitivity matrix stored in Cloudflare R2 and performs bilinear interpolation between the nearest grid points. Response time is typically under 50ms.

Direct endpoint (free, no payment)

No authentication required. Rate limits may apply at high volume. For production agent workflows, use the Qatom MCP tool below.

The commodity parameter name is not currently validated against the ticker's grid axis. Sending ?gold= to a silver-axis ticker will interpolate the value against the silver axis and return a plausible-looking number rather than an error. Always read the echoed inputs object in the response, which names the axis actually used, and send the parameter listed for that ticker in the coverage table above.

Parameters

Response shape

{
  "ticker":        "IVN",
  "model_date":    "2026-06-29",
  "model_version": "v7",
  "inputs": {
    "cu":           6.5,
    "discount_rate": 0.08
  },
  "nav_per_share": 12.05,
  "currency":      "CAD",
  "disclaimer":    "For informational purposes only. Not investment advice."
}

nav_per_share is always accompanied by an explicit currency field (CAD, USD, or AUD depending on the company's model denomination). Never infer currency from the commodity type — IVN uses copper but reports in CAD; ARIS uses gold but reports in USD.

Example calls

# Ivanhoe Mines — copper at $6.50/lb, 8% discount rate
GET /nav-query/ivn?cu=6.5&rate=0.08
→ { "nav_per_share": 12.05, "currency": "CAD" }

# Aris Mining — gold at $4,100/oz, 8% discount rate
GET /nav-query/aris?gold=4100&rate=0.08
→ { "nav_per_share": 59.65, "currency": "USD" }

# Deep Yellow — U3O8 at $82/lb, 8% discount rate
GET /nav-query/dyl?u3o8=82&rate=0.08
→ { "nav_per_share": 3.42, "currency": "AUD" }

# Bunker Hill — zinc axis, 8% discount rate
GET /nav-query/bnkr?zn=1.6&rate=0.08
→ { "currency": "USD", "inputs": { "zinc_usd_per_lb": 1.6, "discount_rate": 0.08 } }

# Hecla Mining — silver axis via the generic `row` parameter, 8% discount rate
# There is no `silver` parameter; `row` is how a silver-axis ticker is reached.
GET /nav-query/hl?row=40&rate=0.08
→ { "currency": "USD", "inputs": { "silver_usd_per_oz": 40, "discount_rate": 0.08 } }

# Seabridge Gold — gold at $4,000/oz, 8% discount rate
GET /nav-query/sa?gold=4000&rate=0.08

Interpolation behaviour

If your input falls between grid points, the Worker performs bilinear interpolation across the nearest four points in the precomputed matrix. If your input is outside the grid range, the Worker clamps to the nearest edge value. The grid ranges are set at model build time and reflected in the sensitivity tables in each PDF report.

Error responses

Qatom MCP — For Autonomous Agents

AI agents that have been granted access to the Qatom MCP marketplace can discover and call Harcourt tools autonomously, with payment settled automatically from the agent's Qatom wallet. No human approval is required per transaction.

NAV Query tool

Tool input schema

{
  "ticker":           "ivn",          // lowercase: aris | ivn | itr | vgc | dyl | sa | hl | bnkr | lug | vzla
  "commodity_param":  "cu",           // gold | cu | u3o8 | zn | row
  "commodity_price":  6.5,            // USD/lb for copper; USD/oz for gold; USD/lb for U3O8
  "discount_rate":    0.08            // decimal (0.08 = 8%)
}

PDF report tools (one per covered company)

Every covered company has its own Qatom tool returning the full NAV PDF report at $15 USD TDN. Rather than enumerate them here — a list that goes stale the moment a company is added — discover them in the Qatom marketplace by provider Harcourt Valuations, or read the authoritative list from the catalog endpoint, where each entry's report_id is also usable directly:

GET https://reports.harcourtvaluations.ai/catalog
Accept: application/json

POST https://reports.harcourtvaluations.ai/
Content-Type: application/json

{ "report_id": "<report_id from the catalog>" }

Agent wallet setup

To call Qatom-gated tools autonomously, an agent needs:

1. A Qatom primary wallet (human-controlled, MFA-gated) — created at todaq.net
2. An agent sandbox wallet (no MFA, funded from the primary wallet via transfer_to_agent_wallet)
3. Sufficient TDN balance to cover the calls ($1 per NAV query, $15 per PDF report)

The agent sandbox wallet is debited automatically when a tool call succeeds. Revenue is credited to Harcourt's provider Twin in real time.

Free Chat API (Klondike Mike)

A free conversational interface to Harcourt's data. Returns plain-language NAV analysis for any covered ticker. No payment required. Useful for quick screening before purchasing a full report or calling the paid API.

// Request
{
  "messages": [
    { "role": "user", "content": "What's the current P/NAV on Ivanhoe Mines?" }
  ]
}

// Response (Anthropic messages format)
{
  "content": [
    {
      "type": "text",
      "text": "IVN is currently trading at approximately 0.96× NAV at copper $6.50/lb..."
    }
  ]
}

The chat agent (Klondike Mike) is built on Claude Haiku. The system prompt is generated server-side from live {ticker}.json files in R2, so it always reflects the most recent published NAV data. Conversation history should be included in the messages array for multi-turn sessions (up to 10 turns retained).

Methodology Notes for AI Consumers

When interpreting Harcourt NAV figures, AI agents and models should be aware of:

• Cash cost, not AISC, in the opex row. All-In Sustaining Cost (AISC) already includes sustaining capex. Using AISC in the opex row while also modelling sustaining capex separately double-counts it, roughly halving free cash flow estimates. Harcourt models use cash cost in opex and model sustaining capex as a separate line.
• Mid-year discounting convention. Cash flows are discounted using the mid-year convention, not end-of-year. This is standard for mining DCF models.
• Discount rates. Base case is typically 8% real discount rate. Sensitivity tables show 5%, 8%, 10%, and 12% depending on the model. Earlier-stage assets use higher rates.
• Resource standards. Canadian-listed companies: NI 43-101 (SEDAR+). US-listed companies: SEC S-K 1300. Australian-listed (currently DYL): JORC 2012.
• Model date. Each report carries a model_date field. Data reflects filings, guidance, and metal prices current at that date. Check model currency before using figures in time-sensitive decisions.
• Currency. NAV per share is denominated in the currency of the company's primary listing (CAD for TSX-primary; USD for NYSE-primary; AUD for ASX-primary). The API currency field is always explicit.
• P/NAV interpretation. A P/NAV below 1.0× means the market is pricing the company below its modelled intrinsic value on an asset basis. Values below 0.5× are common in bear markets or for earlier-stage assets. Values above 1.5× are common for high-quality producers in bull markets. These are market observations, not recommendations.

Disclaimer: Harcourt Valuations reports and API responses are analytical tools for informational purposes only. They do not constitute investment advice, a formal appraisal, or a recommendation to buy or sell any security. All valuations are model estimates subject to uncertainty. AI agents and models using this data must not present it as investment advice to end users without appropriate disclaimers.

Useful Links

• harcourtvaluations.ai — Human-readable website
• harcourtvaluations.ai/api/ — Full API documentation
• harcourtvaluations.ai/company/ — Coverage index; per-company records negotiate HTML or JSON at the same URL
• harcourtvaluations.ai/pricing/ — Pricing for every tier, including agent and adviser access
• harcourtvaluations.ai/faq/ — Methodology questions and answers
• harcourtvaluations.ai/disclaimer/ — What the figures are and are not
• reports.harcourtvaluations.ai/catalog — Live JSON catalog
• reports.harcourtvaluations.ai/sample — Free sample PDF report
• reports.harcourtvaluations.ai/chat — Free chat API (POST)
• harcourtvaluations.ai/llms.txt — llms.txt (plain-text reference)
• todaq.net — Qatom wallet setup for agent access
• Contact: [email protected]