com.ascent-partners/fair-value·Utilities

Fair Value MCP Server

Valuation MCP: DCF/NAV/CCA, WACC, derivatives, credit risk, fixed income, structured products.

Stars
1
Version
0.2.7
License
MIT
Review
Passed
Language
Python
Last commit
2h ago
Forks
0
Open issues
0
Registry update
Oct 14, 2026
financemcpmcp-servermodel-context-protocolvaluation

Connect

remote + pypi
Terminal
$claude mcp add --transport http fair-value https://fair-value.ascent-partners.com/mcp

Headers

Nothing to configure — it works as is.

Security review

Review passed

Reviewed 57m ago.

tools
14 tools scanned
metadata
scanned
packages
1 checked

No findings.

Tools

14
  • calculate_actuarial_pv

    Actuarial present value engine. Discount expected cash flows with mortality, survival, and risk adjustment for insurance and benefit obligations, generalising IFRS 17 (fulfilment cash flows), IAS 19 (employee benefits), IFRS 2 (share-based payments), and IAS 37 (provisions). Use this for regulated IFRS/HKFRS obligations only; it does NOT do generic project or scenario probability weighting (use calculate_expected_value). Methods: ifrs17_gmm: cash_flows, discount_rate, risk_adjustment; ifrs17_paa: premiums, claims_cash, acquisition_cash_flows, coverage_periods; ifrs17_vfa: cash_flows, discount_rate, underlying_items_return, risk_adjustment; ias19_puc: projected_benefits, discount_rate, attribution_years; ias37_provision: outcomes, probabilities, discount_rate, periods. Supply exactly one method with its declared inputs (no defaults). An unknown method, a missing input, or an extra field returns an error envelope (code INVALID_ARGUMENT) instead of raising.

  • calculate_convertible_bond

    Convertible-bond engine. Value callable and puttable convertible or exchangeable bonds with credit risk using a Tsiveriotis-Fernandes lattice (equity discounted at the risk-free rate, debt at a credit spread), with conversion, issuer call, holder put, coupon schedule, and a straight-bond floor. Use this for convertible and exchangeable bonds; for a plain bond or rate curve use calculate_fixed_income, and for a standalone option or warrant use calculate_option. The lattice_tsf, lattice_intensity, finite_difference, lsmc and quantlib methods are alternative numerical schemes for the same valuation and take identical inputs (Tsiveriotis-Fernandes is the reference, lsmc is Monte Carlo, quantlib needs the optional engine); choose one. Methods: lattice_tsf/lattice_intensity/finite_difference/lsmc/quantlib: spot, face, coupon_rate, maturity, conversion_ratio, volatility, risk_free, credit_spread, call_schedule, put_schedule, rights_priority. Supply exactly one method with its declared inputs

  • calculate_credit_loss

    Credit-risk engine (IFRS 9 / HKFRS 9). Compute 12-month, lifetime, and staged expected credit loss, PD/LGD/EAD, provision matrices, hazard rates, and CVA/DVA. Use this for impairment, fair-value credit adjustment, and loan-loss provisioning; for the credit component of a specific convertible bond use calculate_convertible_bond, and for liquidity, control or marketability discounts rather than credit loss use calculate_fair_value_adjustment. Methods: ecl_12m: ead, pd, lgd; ecl_lifetime: ead, pd_lifetime, lgd; ecl_staged: ead, pd_12m, pd_lifetime, lgd, stage; provision_matrix: receivables_ageing, loss_rates; pd_from_spread: credit_spread, recovery, tenor_years; cumulative_pd: annual_pd, years; hazard: hazard_rate, tenor_years; cva_dva: exposure_profile, pd, lgd, discount_rate. Supply exactly one method with its declared inputs (no defaults). An unknown method, a missing input, or an extra field returns an error envelope (code INVALID_ARGUMENT) instead of raising.

  • calculate_dcf

    Discounted cash flow valuation engine. Choose a method and supply its exact inputs to value a business from projected free cash flows, dividends, residual income, or economic profit. Covers FCFF/FCFE DCF, NPV/IRR, terminal values, and multi-stage growth. Use this for going-concern cash-flow businesses; for asset-anchored or financial firms use calculate_residual, for peer-based pricing use calculate_market_multiple, and for pre-profit companies use calculate_loss_making_company. Methods: dcf/npv: cash_flows, discount_rate; annuity: payment, discount_rate, periods; growing_annuity: payment, discount_rate, growth_rate, periods; perpetuity: payment, discount_rate; terminal_gordon: final_cash_flow, discount_rate, perpetual_growth; terminal_multiple: final_cash_flow, exit_multiple; viu_pre_tax: cash_flows, pre_tax_discount_rate; rnpv: cash_flows, discount_rate, probabilities; lease_pv: lease_payments, incremental_borrowing_rate. Supply exactly one method with its declared inputs (no default

  • calculate_discount_rate

    Cost-of-capital engine. Compute WACC, cost of equity (CAPM), cost of debt, unlevered/relevered beta, and country or size premiums from an explicit capital structure and market inputs. Use this to derive the discount rate an income-approach valuation needs; it returns a rate, not a valuation, so feed the result to calculate_dcf, or to calculate_residual for IFRS-basis measurement. Methods: wacc: equity_weight, debt_weight, cost_equity, cost_debt, tax_rate; capm: risk_free, beta, market_return; startup_capm: risk_free, beta, market_risk_premium, size_premium, illiquidity_premium; build_up: risk_free, equity_risk_premium, size_premium, industry_premium, specific_premium; currency_adjusted: base_rate, currency_risk_premium, country_risk_premium; country_risk: sovereign_yield, us_risk_free; esg: base_rate, esg_risk_premium, esg_opportunity_discount; portfolio_beta: weights, betas; ibr: risk_free, credit_spread, tenor_years. Supply exactly one method with its declared inputs (no defaults). A

  • calculate_expected_value

    Expected-value engine. Compute expected values over discrete, continuous, simulated, or tree-structured uncertainty, plus football-field ranges. Use this for generic probability weighting of scenarios, Monte-Carlo and decision trees; it does NOT perform IFRS/HKFRS measurement of provisions, insurance or employee-benefit obligations (use calculate_actuarial_pv), and it does not price path-dependent payoffs (use calculate_structured_product). Methods: discrete: outcomes, probabilities; continuous: distribution, mean, std, lower, upper; scenario: scenarios; monte_carlo: iterations, distributions, base_params, seed; decision_tree: tree; football_field: estimates. Supply exactly one method with its declared inputs (no defaults). An unknown method, a missing input, or an extra field returns an error envelope (code INVALID_ARGUMENT) instead of raising.

  • calculate_fair_value_adjustment

    Fair-value-adjustment engine (IFRS 13). Compute exit-price adjustments including credit, liquidity, control and marketability discounts, blockage, and the fair-value hierarchy level. Use this to move from an indicated value to the fair value recognised in the accounts; for liquidity/marketability inputs of a listed instrument prefer calculate_market_multiple, and for expected credit loss use calculate_credit_loss. Methods: dlom: base_value, restricted_period, volatility, risk_free; dloc: base_value, transaction_cost_pct; control_premium: base_value, control_premium_pct; minority_discount: base_value, minority_discount_pct; highest_best_use: base_value, alternative_use_values; hierarchy_level: inputs. Supply exactly one method with its declared inputs (no defaults). An unknown method, a missing input, or an extra field returns an error envelope (code INVALID_ARGUMENT) instead of raising.

  • calculate_fixed_income

    Fixed-income engine. Price plain coupon bonds, solve for yield to maturity, measure interest-rate sensitivity via Macaulay and modified duration and convexity, and build a HIBOR/HKD-style term structure: bootstrap a zero curve from par rates, infer forward rates, and discount cash flows on the curve. Use this for vanilla bonds, rate risk and discount curves; for convertibles use calculate_convertible_bond and for structured payoffs use calculate_structured_product. Methods: bond_price/duration/convexity: face, coupon_rate, years, ytm, frequency; bond_yield: face, coupon_rate, years, price, frequency; matrix_pricing: target_tenor, benchmark_tenors, benchmark_yields; discount_factor: rate, years, frequency; zero_curve: par_rates, tenors, frequency; forward_rate: zero_rates, tenors, t1, t2; pv_curve: cash_flows, times, zero_rates, tenors. Supply exactly one method with its declared inputs (no defaults). An unknown method, a missing input, or an extra field returns an error envelope (code

  • calculate_loss_making_company

    Loss-making-company engine. Value currently unprofitable companies with margin-ramp DCF, revenue multiples, Merton structural equity, the VC method, distressed waterfalls, bank residual income, and SPAC deals; every method returns a central value plus a dispersion (sigma, percentiles, long-tail). Use this when earnings-based multiples break down; for standalone probability weighting of arbitrary scenarios use calculate_expected_value, and for a single going-concern DCF use calculate_dcf. Methods: margin_ramp_dcf: revenue, growth_rate, start_margin, target_margin, ramp_years, discount_rate, years, shares_outstanding, net_debt, range_method; revenue_multiple: revenue, ev_revenue_multiple, net_debt, shares_outstanding, range_method; merton_equity: firm_value, firm_volatility, debt, risk_free, maturity, range_method; vc_method: terminal_value, target_return, investment, shares_outstanding, range_method; distressed_waterfall: enterprise_value, claims, range_method; bank_residual_income: boo

  • calculate_market_multiple

    Market-multiple engine. Apply peer multiples (P/E, P/B, EV/EBITDA, EV/Sales, PEG and more) or derive implied multiples to price a company on a comparable basis. Use this for market-approach pricing where peers exist; it does peer multiples only — for intrinsic cash-flow value use calculate_dcf, and for residual-income or IFRS-basis measurement use calculate_residual. Methods: ev_revenue: revenue, ev_revenue_multiple; ev_ebitda: ebitda, ev_ebitda_multiple; ev_arr: arr, ev_arr_multiple; ev_gmv: gmv, ev_gmv_multiple; pe: eps, pe_multiple; pb: book_value_per_share, pb_multiple; ps: sales_per_share, ps_multiple; cap_rate: net_operating_income, cap_rate; regression: intercept, growth_rate, growth_coefficient, market_maturity, maturity_coefficient; royalty_cap: revenue, royalty_rate, discount_rate; ddm: dividend_per_share, cost_equity, growth_rate. Supply exactly one method with its declared inputs (no defaults). An unknown method, a missing input, or an extra field returns an error envelope

  • calculate_option

    Option-pricing engine. Price European and American options and warrants (Black-Scholes, Black-76, CRR binomial, Garman-Kohlhagen FX, digital, range, share-based) and their greeks. Use this for a single contingent claim or warrant on one underlying; it does NOT price listed structured payoffs such as CBBCs, inline/derivative warrants or autocallables (use calculate_structured_product). Methods: black_scholes: spot, strike, maturity, risk_free, volatility, option_type; black76: forward, strike, maturity, risk_free, volatility, option_type; binomial_american: spot, strike, maturity, risk_free, volatility, option_type, steps; garman_kohlhagen: spot, strike, maturity, domestic_rate, foreign_rate, volatility, option_type; barrier_first_passage: spot, strike, maturity, risk_free, volatility, option_type, barrier, barrier_type; asian_average: spot, strike, maturity, risk_free, volatility, option_type, average_type; digital: spot, strike, maturity, risk_free, volatility, cash_payout; range: spo

  • calculate_residual

    IFRS/HKFRS measurement engine. Compute goodwill and purchase-price allocation, impairment (IAS 36), inventory net realisable value, held-for-sale, debt waterfalls, cap tables, sum-of-the-parts and SPAC redemption; residual income and justified price-to-book; and non-financial asset fair value: investment property (IAS 40 / HKAS 40), PP&E revaluation via depreciated replacement cost (IAS 16) and biological assets at fair value less costs to sell (IAS 41). Use this for accounting-basis measurement of assets and equity; for going-concern cash flow use calculate_dcf and for peer multiples use calculate_market_multiple. Methods: goodwill: purchase_price, fair_value_net_identifiable_assets; ppa: purchase_price, tangible_assets_fv, identified_intangibles_fv; impairment_fvlcd: carrying_value, fair_value_less_costs_to_dispose; impairment_viu: carrying_value, value_in_use; inventory_nrv: carrying_value, net_realisable_value; held_for_sale: carrying_value, fair_value_less_costs_to_sell; debt_wate

  • calculate_sector_metrics

    Sector-metric engine. Compute the metrics that anchor valuation in specific industries: SaaS (ARR, NRR, magic number, Rule of 40), marketplaces (take rate, GMV multiple), lending (LTV/CAC), and crypto (NVT, Metcalfe). It returns operating metrics, not a valuation; use them as inputs to calculate_market_multiple or calculate_dcf. Methods: ltv: arpu, gross_margin, churn_rate; cac: sales_marketing_expense, new_customers; arr: subscription_values; nrr: starting_revenue, ending_revenue, expansion_revenue; magic_number: net_new_arr, sales_marketing_expense_prior; rule_of_40: growth_rate, profit_margin; take_rate: revenue, gmv; gmv_multiple: gmv, ev_gmv_multiple; retention: retained_customers, starting_customers; trl: market_size, market_share, margin, exit_multiple, trl_discount; break_even: fixed_costs, asp, variable_cost; gross_margin: asp, variable_cost; token: transaction_volume, price_per_tx, velocity, supply; nvt: market_cap, transaction_volume; metcalfe: n, coefficient. Supply exactly

  • calculate_structured_product

    Structured-product engine. Value HKEX-listed and OTC structures: CBBCs, derivative and inline warrants, equity-linked notes and investments, autocallables, accumulators and decumulators, credit-linked notes, TRS, and CFDs. Use this for equity-linked and credit-linked payoff structures; for a plain option or warrant use calculate_option, for a convertible or exchangeable bond use calculate_convertible_bond, and for a vanilla bond or term structure use calculate_fixed_income. Methods: cbbc: notional, spot, strike, barrier, barrier_type, maturity, risk_free, volatility, option_type; cbbc_residual: notional, spot, call_price, entitlement, barrier, barrier_type, maturity, risk_free, volatility, option_type; derivative_warrant: notional, spot, strike, maturity, risk_free, volatility, average_type, option_type; inline_warrant: notional, spot, lower_strike, upper_strike, maturity, risk_free, volatility, payout; inline_warrant_avg: notional, spot, lower_strike, upper_strike, maturity, risk_free

Fair Value

PyPI CI License: MIT MCP Registry TDQS

Professional financial valuation system for OpenCode with IFRS/IVS compliance.

mcp-name: com.ascent-partners/fair-value

Overview

A single valuation core — exposed as an MCP server, a REST API, and a Python library — whose 14 native calculate_* tools / 135 methods cover corporate, startup, and intangible valuation aligned to IVS 2025 and IFRS/IAS:

  • DCF / NAV / CCA / residual income, market multiples, cost of capital (WACC, Fama-French 5-Factor, build-up)
  • Options, fixed income (term-structure curves), convertible bonds, structured products
  • IFRS 9 / HKFRS 9 credit risk (ECL, PD/LGD, CVA/DVA), actuarial PV (IFRS 17, IAS 19, IAS 37)
  • Fair-value adjustments (IFRS 13), expected value, and loss-making-company methods

Every result is a deterministic-first envelope carrying the centre value, solution_type, statistics (σ / percentiles, and seeded samples for the few stochastic methods), and citations resolving to verbatim IVS/IFRS clauses. 120 / 135 methods carry standards citations and the taxonomy has 0 orphan clauses, enforced by a conformance gate in CI.

Quick start (≤ 5 minutes)

Fastest path — no install:

  • Hosted MCP (Streamable HTTP): https://fair-value.ascent-partners.com/mcp
  • Hosted REST: https://fair-value.ascent-partners.com/v1/health
  • Frontage & docs: https://fair-value.ascent-partners.com/
  • Run locally, no install: uvx --from "fair-value[mcp]" fair-value-mcp

Then call any of the 14 calculate_* tools (add -help / help=true for the generated transparency record). Client config: MCP Server.

Architecture

flowchart LR
  CLIENT["AI agent / OpenCode"] -->|"stdio (uvx) or Streamable HTTP"| MCP["fair-value-mcp<br/>14 calculate_* tools · 135 methods"]
  HOST["Hosted · fair-value.ascent-partners.com<br/>docs/landing at / · MCP at /mcp · REST at /v1"] --> CLIENT
  MCP --> REG["method-spec registry<br/>(valuation://methods)"]
  REG --> STD["standards taxonomy + corpus<br/>IVS 2025 · IFRS/IAS · (valuation://standards)"]
  REG --> CORE["valuation engine<br/>DCF · NAV · CCA · WACC (FF5) · derivatives<br/>credit risk · actuarial"]
  CORE --> DATA["inputs from apdb-etl (cited)"]
  CORE --> ENV["result envelope<br/>value + statistics + citations"]

Installation

pip install -r requirements.txt   # dev workflow
# or, as a package:
pip install .                     # base library
pip install ".[mcp]"              # + MCP server dependencies (fastmcp)

The console command fair-value-mcp runs the MCP server (stdio; add --http for Streamable HTTP).

MCP Server

# run locally without installing (stdio)
uvx --from "fair-value[mcp]" fair-value-mcp

# or install and run
pip install "fair-value[mcp]"
fair-value-mcp            # stdio
fair-value-mcp --http     # Streamable HTTP

The server exposes 14 native calculate_* tools spanning DCF, cost of capital, market multiples, residual/asset valuation, options, expected value, credit risk, actuarial PV, sector metrics, fair-value adjustments, convertible bonds, structured products, loss-making companies, and fixed income — all derived from one method-spec registry. Add -help to any tool (or help=true) for its generated documentation with formula reference, inputs, and governing clauses.

Adoption target: ≥ 100 PyPI downloads and ≥ 1 directory listing within 90 days of the first release (tracked via the PyPI stats API and the directory listing).

REST API

The same core is exposed at /v1 (served next to MCP by mcp_server.asgi:app):

curl -s localhost:8000/v1/health
curl -s -X POST localhost:8000/v1/calculate/calculate_dcf \
  -H 'content-type: application/json' \
  -d '{"method":"dcf","cash_flows":[100,110],"discount_rate":0.1}'

Endpoints: /v1/health, /v1/tools, /v1/methods, /v1/standards, /v1/openapi.json, /v1/docs (Swagger UI), /v1/help/{tool}, POST /v1/calculate/{tool}. See REST API.

Web frontage (Next.js)

The hosted domain serves a Next.js frontage — landing, complete docs, methods catalogue (one page per method), standards browser, and an API playground — alongside the MCP/REST function in one Vercel project. It is data-driven: the catalogue is generated from the registry at build time (scripts/gen_web_data.py → data/catalog.json).

pnpm install
pnpm dev          # http://localhost:3000  (expects /v1 from the API for the playground)
pnpm build        # prebuild regenerates data/catalog.json
pnpm typecheck && pnpm lint

Routing: / and /docs/* are Next.js; /mcp and /v1/* are rewritten to the Python function (api/index.py). The frontage is localized — en at /, zh at /zh, hk at /hk — via per-locale root layouts with hreflang.

Quick Start (Python)

from valuation_engine import run_valuation

result = run_valuation('9988.HK', 'dcf')  # DCF valuation (shared envelope)

Standards & citations

The standards alignment is data, not code: standards/taxonomy.json maps each method to its IVS and IFRS/IAS clauses, standards/source/*.md holds the verbatim clause text (with standards/provenance.json recording edition and source), and standards/coverage-baseline.json is the coverage ratchet. The engine attaches solution_type and citations to every envelope, and scripts/check_conformance.py fails CI if a published method loses its citation or the taxonomy/corpus drifts. See Standards reference.

Module structure

flowchart LR
  SEED["method_spec_seed.py<br/>method tables · 135 methods"] --> SPEC["method_spec.py<br/>parameter vocabulary"]
  SPEC --> SURF["tool_surface.py<br/>15 calculate_* tools"]
  SPEC --> STD["standards.py<br/>taxonomy · citations"]
  SURF --> SRV["server.py (FastMCP)"]
  SRV --> STDIO["stdio · uvx fair-value-mcp"]
  SRV --> HTTP["Streamable HTTP · fair-value-mcp --http"]
  ASGI["asgi.py (+ rest.py, openapi.py)"] --> HOST["Hosted · / + /v1"]
  SRV --> DOCS["docs.py<br/>-help transparency records"]
  STD -.->|resources| RES["valuation://methods · valuation://standards"]
  SRV -.-> DOCS
src/
├── constants.py            # standards references
├── valuation/              # DCF, NAV, CCA, asset standards (relief-from-royalty, MPEEM, residual)
├── cost_of_capital/        # WACC, FF5, KMV
├── credit_risk/            # ECL, PD/LGD, CVA/DVA
├── derivatives/            # options, swaps, convertible bonds, structured products, fixed income
└── output/                 # shared result envelope (value + statistics + citations)
mcp_server/
├── method_spec.py + method_spec_seed.py   # single source of truth for tools/methods
├── standards.py                           # taxonomy loader, citations, coverage
├── tool_surface.py · engine.py · handlers.py · server.py
├── docs.py · rest.py · openapi.py · asgi.py
└── catalog.py · prompts.py                # valuation:// resources + guided prompts
standards/                                 # taxonomy.json · source/*.md · provenance · baseline
scripts/                                   # check_conformance.py · gen_docs.py

Request lifecycle

sequenceDiagram
    autonumber
    participant C as MCP / REST / Python caller
    participant E as validation + dispatch
    participant R as method-spec registry
    participant S as standards taxonomy
    participant M as computation modules (src/)
    participant O as output envelope
    C->>E: calculate_*(...) / POST /v1/calculate/*
    E->>R: resolve method + validate parameters (no defaults)
    R-->>E: method spec
    E->>M: dispatch to valuation / cost_of_capital / credit_risk / derivatives
    E->>S: attach solution_type + citations
    M-->>E: value + steps + assumptions
    E->>O: ok() / error() envelope (value · statistics · citations)
    O-->>C: status · method · value · statistics · assumptions · citations · disclaimer

Requirements

  • Python 3.10+
  • pandas, numpy, scipy, python-dateutil
  • fastmcp (MCP extra), openpyxl, pdfplumber, python-docx
  • QuantLib, pandas_datareader, pytesseract/easyocr (all optional, with native fallbacks)

Documentation

Standards compliance

  • IVS 2025 — International Valuation Standards (103, 105, 210, 220, 230, 300, 400, 410, 500)
  • IFRS 13 Fair Value Measurement; IFRS 9 Financial Instruments; IFRS 16 Leases; IFRS 17 Insurance Contracts
  • IAS 36 Impairment of Assets; IAS 19 Employee Benefits; IAS 37 Provisions, Contingent Liabilities and Contingent Assets

License

Released under the MIT License.

From the server's repository — third-party content, read it before running anything it suggests.

More in Utilities

Listing from the official MCP Registry · repository facts from GitHub, 1h ago.