Skip to main content
Glama
deenesjakoruzh
DanCastHub

awardmath-mcp

by DanCastHub
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Servidor MCP de AwardMath

awardmath-mcp conecta asistentes de IA a la API pública de AwardMath mediante el Model Context Protocol.

AwardMath es el optimizador de puntos de viaje. Tú proporcionas tus saldos de puntos y un objetivo de viaje. Un solucionador determinista busca en un grafo versionado de ratios de transferencia y tablas de canje, y devuelve hasta tres planes de canje verificados y explicables.

Los cálculos consisten en enumerar y puntuar sobre las tablas publicadas. Un LLM puede interpretar tu pregunta y explicar los resultados, pero nunca elige ni optimiza los planes.

Este repositorio contiene el servidor MCP y una instantánea gratuita de datos en data/. El servidor es de solo lectura. No requiere tarjeta de API, inicio de sesión ni suscripción, y no hace scraping de sitios de aerolíneas.

Herramientas

El servidor expone tres herramientas.

Herramienta

Qué hace

list_programs

Lista los programas rastreados y gastables

solve_award_trip

Devuelve hasta tres planes

parse_wallet

Estructura el texto de la cartera

list_programs

list_programs devuelve todos los programas que AwardMath rastrea e identifica qué IDs de programa se pueden gastar hoy en una ejecución.

Los programas gastables incluyen programas de canje con tablas tarifadas y monedas bancarias que se transfieren a uno de esos programas. Esta distinción evita que un asistente le pida al solucionador gastar un saldo que no tiene ningún camino hacia un canje con precio.

solve_award_trip

solve_award_trip busca planes que encajen con tu cartera, orígenes, destinos, cabinas, número de viajeros y tope de efectivo.

Si se obtiene una respuesta correcta, contiene hasta tres planes con:

  • Pasos exactos de transferencia

  • Puntos totales requeridos

  • Cargos tarifados

Si ningún plan encaja, la respuesta incluye no_plan_reasons. Estos motivos identifican la restricción que ha fallado, en lugar de rellenar el hueco con una ruta o un precio inventado.

parse_wallet

parse_wallet convierte texto libre en saldos con estructura.

Por ejemplo:

250k Amex, 80k Chase

Los saldos claros se convierten en IDs de programa y cantidades. Las expresiones ambiguas se muestran para aclararlas, en lugar de asignarlas a un programa por conjetura.

Related MCP server: mcp-travelcode

Configuración

Puedes ejecutar el servidor directamente desde GitHub o instalarlo desde un clon.

Claude Code

claude mcp add awardmath -- uvx --from git+https://github.com/DanCastHub/awardmath-mcp awardmath-mcp

Claude Desktop u otro cliente MCP configurado con JSON

{
  "mcpServers": {
    "awardmath": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/DanCastHub/awardmath-mcp", "awardmath-mcp"]
    }
  }
}

Desde un clon

pip install -e .
awardmath-mcp

No se requiere ninguna clave de API ni cuenta en AwardMath.

Ejemplo

Pide a tu asistente un plan tarifado con los saldos que ya tienes.

Tú: Tengo 60.000 puntos de Amex Membership Rewards. Encuentra un asiento en clase económica de LAX a HNL.

Asistente: A fecha de 2026-08-23, el plan con mejor precio usó 16.000 Avios de Qatar para el asiento, financiado a través de una transferencia de Amex a 1:1. El resultado incluye los pasos exactos de transferencia, el total de puntos y los cargos. No confirma que el asiento esté disponible.

Ese resultado tiene una fecha asociada porque los ratios de transferencia y los precios de los canjes cambian. Ejecuta una nueva búsqueda, confirma el asiento de canje y revisa las condiciones de transferencia antes de mover los puntos.

El conjunto de datos

El directorio data/ ofrece una instantánea fechada del grafo del programa de puntos y la salida ya calculada del solucionador.

data/transfer-ratios-current.csv

Este archivo contiene 109 aristas de transferencia banco-progr desde ocho monedas de origen, observadas el 2026-08-23.

Cada fila refleja la observación más reciente que AwardMath ha verificado contra la página del programa o ha corroborado entre fuentes independientes. Las afirmaciones editoriales que no se habían verificado quedaron excluidas.

Las columnas incluyen:

  • Ratio de transferencia

  • Comisiones

  • Tiempo de transferencia, cuando se observa

  • Estado de verificación

  • Fecha de observación

Los ratios cambian. Trata cada fila como válida solo en la fecha de observación correspondiente y vuelve a consultar el programa antes de transferir puntos.

data/sample-solved-plans.json

Este en archivo contiene cinco escenarios ejecutados con el solucionador en directo el 2026-08-23.

Cuatro de esos escenarios han producido planes. Entre ellos:

  • LAX a HNL en clase económica con 60.000 puntos de Amex Membership Rewards

  • SFO a HND en clase business con 100.000 puntos de Amex Membership Rewards, tarifado mediante ANA a 82.500 puntos

Uno es deliberadamente vacío. La búsqueda de YVR a DXB en clase business muestra cómo responde el solucionador cuando el grafo no puede dar precio a una ruta. En su lugar, indica la cobertura del grafo que falta en vez de inventar un plan.

Qué no se incluye

El conjunto de datos es una instantánea, no el producto AwardMath completo.

El historial versionado que lo acompaña queda en awardmath.com. Este historial registra ratios y tarifas a lo largo del tiempo y sirve para consultar el historial de precios y de reservar ahora o esperar. It is not other in this repo.

Lo que este servidor no hará

El servidor no comprueba la disponibilidad de asientos de canje en tiempo real.

Los planes se valoran a partir de tablas de canje públicas y de relaciones de transferencia publicadas. Una ruta puede ser matemáticamente valida pero no tener asientos disponibles en tus fechas.

Antes de mover ningún punto:

  1. Confirma el espacio del canje mediante Seats.aero, PointsYeah, e o la aerolínea.

  2. Comprueba el precio en puntos y el importe en efectivo en la tabla del programa con el que quieres reservar.

  3. Vuelve a consultar el ratio y las condiciones de la transferencia.

Las transferencias son irreversibles. No transfieras solo porque el solucionador haya encontrado un camino con precio. Transfiere únicamente después de haber confirmado que el asiento se puede reservar.

AwardMath comprueba los cálculos. Tú confirma el asiento.

Licencias

El código está publicado bajo la Licencia MIT.

Los archivos que hay en data/ están publicados bajo CC BY 4.0. Usa esta atribución con un enlace:

Datos: Datos y canje

Fuentes:

Available Tools

3 tools
list_programsA

List every rewards program AwardMath tracks.

Returns {"names": {program_id: display name}, "plannable": [program_id]}. "plannable" ids are the ones a solve can spend today: award programs with priced charts, plus bank currencies that transfer into one. Use these ids in solve_award_trip wallets.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.4/5.0
Behavior4/5

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It precisely outlines the return structure (an object with 'names' and 'plannable' fields) and elaborates on the meaning of 'plannable' (award programs with priced charts plus bank currencies that transfer into one). This gives the agent solid insight into what the tool returns and on what basis, well beyond a generic 'list' statement.

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

Conciseness5/5

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

The description is three concise sentences: the first states the purpose, the second defines the return shape, and the third explains the 'plannable' field and its intended use. Every sentence contributes meaningful information with no redundancy or padding, making it efficiently structured and easy to parse.

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?

Given that the tool has no parameters and no output schema, the description is exceptionally complete. It fully defines the return object, explains the semantics of each field, and explicitly ties the output to the sibling tool solve_award_trip. There are no critical gaps that would prevent an agent from correctly invoking the tool and interpreting its results.

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

Parameters4/5

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

The tool has zero parameters and the input schema is empty, so the description has no parameter semantics to add. Per the rubric, a tool with zero parameters gets a baseline of 4. The description appropriately focuses on output and usage rather than parameters, so the score reflects this baseline.

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

Purpose4/5

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

The description begins with 'List every rewards program AwardMath tracks,' which is a clear verb and resource definition. It does not explicitly differentiate from sibling tools like parse_wallet or solve_award_trip, but the listing nature is unmistakable given the name and the different purposes of those siblings. Thus it is specific but lacks explicit sibling distinction.

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

Usage Guidelines5/5

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

The description goes beyond just stating what it does by explaining when to use the output: 'Use these ids in solve_award_trip wallets.' This directly connects the tool to a sibling and prescribes how the returned 'plannable' ids should be consumed. It also clarifies which programs qualify as 'plannable,' giving the agent a clear decision rule for usage.

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

parse_walletA

Turn free text about points balances into structured wallet entries.

Example input: "I have 250k Amex MR, 80k Chase, and my wife has 60k Alaska". Returns {"balances": [{owner, program, balance, expires}], "unrecognized": [...], "needs_clarification": [...]}. Anything ambiguous lands in the latter two lists instead of being guessed — show it to the user rather than dropping it. If you already know the balances in structured form, skip this and build the wallet directly.

ParametersJSON Schema
NameRequiredDescriptionDefault
textYes

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers: it spells out the return shape (balances, unrecognized, needs_clarification), and crucially states the no-guessing policy — 'Anything ambiguous lands in the latter two lists instead of being guessed — show it to the user rather than dropping it.' This is a meaningful behavioral trait. It stops short of edge-case handling (e.g., empty text), keeping it from a 5.

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

Conciseness4/5

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

The description is front-loaded with the purpose, followed by a compact example, the return schema, and the behavioral contract. Each sentence earns its place. It runs slightly long due to the dual example-and-schema-format block, but nothing is redundant.

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

Completeness4/5

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

For a single-parameter parse tool with no output schema, the description is nearly complete: it states the input, enumerates the three output lists, and defines the ambiguity contract. The absence of an output schema means the description must explain return values, which it does. Minor omission: it doesn't state a reasonable fallback for degenerate input, but the tool's complexity doesn't demand it.

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 description coverage is 0% for the single required parameter, so the description must compensate. The example input ('I have 250k Amex MR, 80k Chase...') conveys the expected free-text format with program names and amounts, which is the main semantic need. However, the description never explicitly defines the parameter's contract beyond the example — it leaves the agent to infer that text is a raw user message about point balances.

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?

The opening line 'Turn free text about points balances into structured wallet entries' uses a specific verb (turn/parse), a defined resource (free text about points balances), and a concrete outcome (structured wallet entries). It clearly differentiates from siblings list_programs and solve_award_trip, which serve materially different purposes.

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?

The description provides an explicit when-not-to-use condition: 'If you already know the balances in structured form, skip this and build the wallet directly.' This tells an agent precisely when the tool is unnecessary. It implies when to use it (when balances exist only as free text) via the example, though it doesn't formally exclude siblings — acceptable since the siblings are not genuine alternatives to a text-parsing operation.

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

solve_award_tripA

Compute up to three verified award-booking plans for a trip.

wallet: [{"owner": "me", "program": "amex-mr", "balance": 250000}] — ids from list_programs; "expires" (ISO date) optional per entry. origins / destinations: IATA airport codes, e.g. ["LAX"] -> ["HNL"]. cabins: any of "economy", "premium", "business", "first" (default economy). max_cash_usd: cap on out-of-pocket cash (fees, points purchases). window_from / window_to: ISO dates, optional.

Returns plans with exact transfer steps, points math, and fees, plus no_plan_reasons when nothing works — an empty result explains itself. Plans price the award from published charts; they never assert live seat availability, so tell the user to confirm space before transferring anything irreversible.

ParametersJSON Schema
NameRequiredDescriptionDefault
cabinsNo
walletYes
originsYes
travelersNo
window_toNo
window_fromNo
destinationsYes
max_cash_usdNo

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries full responsibility. It explicitly states plans are priced from published charts and never assert live seat availability, and that empty results include no_plan_reasons. This is a strong disclosure of key behavioral limitations and return expectations, though it doesn't cover every potential edge case.

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

Conciseness4/5

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

The purpose is front-loaded, followed by a systematic per-parameter breakdown and behavioral caveats. The text is longer than average but every sentence adds value; there is no fluff or redundant wording.

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

Completeness4/5

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

For a tool with 8 parameters, no annotations, and no output schema, the description covers purpose, inputs, high-level output (plans with transfer steps, points math, fees, no_plan_reasons), and a critical limitation (no live availability). It does not describe the exact output structure, but the summary is sufficient for an agent to call and interpret results.

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

Parameters4/5

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

Schema coverage is 0%, so the description must compensate. It explains wallet with an example, origins/destinations with IATA codes, cabins with options and default, max_cash_usd as a cap, and window dates as ISO optional. It covers 7 of 8 parameters but omits 'travelers', leaving its meaning to inference—a minor but notable gap.

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?

The description opens with a specific verb-resource pair ('Compute up to three verified award-booking plans for a trip') and the context clearly distinguishes it from siblings list_programs and parse_wallet. The 'verified' and 'up to three' qualifiers add specificity without ambiguity.

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?

The description provides clear context for when to use the tool: after obtaining wallet IDs from list_programs, and it instructs the agent to confirm live availability before irreversible transfers. It does not explicitly name alternatives or exclusions, but the sibling relationships are implicit, so this is adequate.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv0.1.0
    • First observedlist_programs
    • First observedparse_wallet
    • First observedsolve_award_trip
Deploy Server
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

TDQS

A4.4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: list_programs enumerates available programs, parse_wallet converts free text into structured wallet entries, and solve_award_trip computes booking plans. There is zero overlap between them, so an agent can easily select the right tool for each step of the workflow.

Naming Consistency5/5

All three tool names follow a consistent verb_noun pattern: list_programs, parse_wallet, solve_award_trip. The verbs are clear and the nouns match the domain, making the naming predictable and intuitive.

Tool Count5/5

Three tools is well-scoped for the server's purpose: listing programs, parsing input, and solving trips. Each tool is necessary and sufficient for the end-to-end workflow, with no redundancy or missing helper clutter.

Completeness4/5

The tools cover the full lifecycle: discovering what programs exist, structuring user input, and computing booking plans with transfer steps. A minor gap is the lack of a dedicated tool for fetching detailed program rules or live availability, but the solve tool's output includes sufficient details and reasons for failures, so most practical needs are met.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers