Tako

Plugin (recomendado) — instala la conexión MCP más las habilidades de investigación incluidas de Tako en un solo paso, y funciona de inmediato en el nivel gratuito — sin necesidad de acuñar o gestionar una clave API:

claude plugin marketplace add TakoData/tako-mcp
claude plugin install tako@tako

Eso es todo: tako_search funciona de inmediato en el nivel gratuito anónimo. Para desbloquear el conjunto completo de herramientas y tus propios límites de cuenta, autentícate una vez con OAuth: ejecuta /mcp dentro de Claude Code, selecciona tako y elige Autenticar. Se abre un navegador para que inicies sesión con tu cuenta de Tako y se acuña automáticamente una clave API por host para ti (visible y revocable en tako.com/console/api-keys). El mismo flujo OAuth impulsa el plugin en Claude.ai: el conector Tako del plugin se conecta con un clic, sin pegar tokens.

Si previamente agregaste el servidor con claude mcp add, elimínalo primero (claude mcp remove tako-mcp) para no terminar con dos copias de cada herramienta.

¿Actualizando desde una versión anterior del plugin? Las versiones anteriores pedían una clave API de Tako en la configuración del plugin; ese ajuste ya no existe, así que después de actualizar tu conexión aterriza silenciosamente en el nivel anónimo (tako_search funciona; el resto te pide iniciar sesión) — nada falla, pero tus límites de cuenta ya no están activos. Ejecuta /mcp → tako → Autenticar una vez (o usa el botón Conectar en Claude.ai) para restaurar el acceso autenticado completo.

O agrega el servidor MCP directamente (luego autentícate en el lugar vía /mcp → tako → Autenticar):

claude mcp add tako --transport http https://mcp.tako.com/mcp

Verifica con claude mcp list (debería mostrar tako conectado) o /mcp dentro de una sesión.

Usa la insignia de un clic de arriba, o agrega a ~/.cursor/mcp.json — Cursor te pedirá iniciar sesión en el primer uso:

{
  "mcpServers": {
    "tako": {
      "type": "http",
      "url": "https://mcp.tako.com/mcp"
    }
  }
}

Agrega a tu configuración MCP de Windsurf — Windsurf te pedirá iniciar sesión en el primer uso:

{
  "mcpServers": {
    "tako": {
      "type": "http",
      "url": "https://mcp.tako.com/mcp"
    }
  }
}

Agrega a .vscode/mcp.json (espacio de trabajo) o a tu mcp.json de usuario — VS Code te pedirá iniciar sesión en el primer uso:

{
  "servers": {
    "tako": {
      "type": "http",
      "url": "https://mcp.tako.com/mcp"
    }
  }
}

Extensión (recomendada) se instala con un comando y funciona de inmediato en el nivel gratuito sin necesidad de acuñar o gestionar una clave API:

gemini extensions install https://github.com/TakoData/tako-mcp

Eso instala la conexión MCP, las habilidades de investigación incluidas de Tako y tres comandos:

Para desbloquear el conjunto completo de herramientas y tus propios límites de cuenta, autentícate una vez: ejecuta /mcp auth tako dentro de Gemini CLI. Se abre un navegador para que inicies sesión con tu cuenta de Tako, y se acuña automáticamente una clave API por host para ti (visible y revocable en tako.com/console/api-keys).

Configuración manual: si prefieres no instalar la extensión, o quieres fijar una lista de permitidos ?tools=, agrega a ~/.gemini/settings.json (autentícate luego con /mcp auth tako):

{
  "mcpServers": {
    "tako": {
      "httpUrl": "https://mcp.tako.com/mcp"
    }
  }
}

Para usar una clave API en su lugar, agrega un bloque headers con "Authorization": "Bearer <key>" — pero complétalo por completo: Gemini sustituye las referencias ${VAR} no establecidas literalmente, y un encabezado Authorization malformado se rechaza en lugar de ignorarse, así que un token a medias rompe la conexión donde ningún token habría funcionado.

Agrega a opencode.json — OpenCode te pedirá iniciar sesión en el primer uso:

{
  "mcp": {
    "tako": {
      "type": "remote",
      "url": "https://mcp.tako.com/mcp",
      "enabled": true
    }
  }
}

Codex se conecta a servidores remotos a través del puente mcp-remote, que ejecuta el flujo de inicio de sesión en tu navegador en la primera conexión:

[mcp_servers.tako]
command = "npx"
args = ["-y", "mcp-remote", "https://mcp.tako.com/mcp"]

Agrega a settings.json de Zed (vía el puente mcp-remote, que ejecuta el flujo de inicio de sesión en tu navegador en la primera conexión):

{
  "context_servers": {
    "tako": {
      "source": "custom",
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.tako.com/mcp"]
    }
  }
}

Los hosts de chat de consumo no aceptan tokens Bearer. claude_desktop_config.json solo valida servidores stdio, así que una entrada "type": "http" remota allí se descarta silenciosamente — Claude Desktop se conecta a través de Conectores como Claude.ai. El endpoint alojado ejecuta un flujo OAuth 2.1 que te inicia sesión con tu cuenta de Tako y acuña una clave por host automáticamente.

Requisitos previos: solo inicia sesión en tako.com con la identidad que autorizarás. No acuñas un token tú mismo — el flujo de consentimiento crea una clave por host (llamada MCP: <client>, visible y revocable en tako.com/console/api-keys). Conectar un nuevo host nunca rota la clave de otro host; Tako recorta tu clave MCP más antigua después de diez.

Claude.ai (requiere Pro, Max, Team o Enterprise)

1. Abre Claude.ai → Configuración → Conectores
2. Haz clic en Agregar conector personalizado
3. Pega https://mcp.tako.com/mcp y haz clic en Conectar
4. Completa el flujo de inicio de sesión de Tako; Tako aparece entonces como conectado

Claude Desktop (mismo requisito de plan que Claude.ai)

1. Abre Claude Desktop → Configuración → Conectores
2. Haz clic en Agregar conector personalizado
3. Pega https://mcp.tako.com/mcp y haz clic en Conectar
4. Completa el flujo de inicio de sesión de Tako; Tako aparece entonces como conectado

ChatGPT — instala la aplicación Tako desde el directorio de aplicaciones de ChatGPT (se conecta vía OAuth y usa la superficie de la aplicación en https://mcp.tako.com/mcp/chatgpt). Para agregarla manualmente como conector personalizado en su lugar (requiere Pro, Business o Enterprise; Modo Desarrollador habilitado):

1. Abre ChatGPT → Configuración → Conectores → Modo Desarrollador y actívalo
2. Haz clic en Crear conector personalizado
3. Pega https://mcp.tako.com/mcp/chatgpt y haz clic en Conectar
4. Completa el flujo de inicio de sesión de Tako; el conector aparece entonces listado y listo

La superficie /mcp/chatgpt es solo OAuth y está ajustada para ChatGPT (widget de gráfico interactivo, una lista fija de cinco herramientas; ?tools= se ignora allí). La URL genérica /mcp también funciona allí — obtienes imágenes de gráfico en lugar del widget interactivo.

Durante la conexión verás tres pantallas alojadas por Tako independientemente del host: una página de inicio de sesión (Google, o tu correo y contraseña de Tako), una página de consentimiento ("Conectar [host] a Tako — Permitir / Cancelar"), y luego un retorno al host. El host puede mostrar su propio aviso de consentimiento también — eso es normal.

Desconexión. Una desconexión por host (eliminar el conector en la configuración del host) detiene solo ese host; otros hosts y clientes con autenticación Bearer siguen funcionando. Para matar todo de forma definitiva, rota tu clave en tako.com/console/api-keys — cada concesión emitida previamente en cada host deja de autenticarse de inmediato.

Dos herramientas, a un paso de distancia — tako_search encuentra, tako_contents obtiene:

• Preguntas amplias o de múltiples partes → búsquedas estrechas en paralelo. Descompón en consultas de una sola entidad y métrica ejecutadas simultáneamente — p. ej. "inflación IPC de EE. UU.", "inflación IPC subyacente de EE. UU.", "inflación PCE de EE. UU." — y luego sintetiza tú mismo.
• No estás seguro de qué cubre Tako → tako_available_data primero. Es gratuito, devuelve el nombre exacto de la métrica para buscar, y si falla, aún queda la búsqueda web.

Pregunta específica → busca, luego obtén las filas:

1. El usuario pregunta: "¿Cuál fue el PIB de EE. UU. en 2024?"
2. El agente llama a tako_search; la primera tarjeta lleva el valor destacado y su gráfico
3. Para la serie en sí, el agente llama a tako_contents en la url de esa tarjeta, y luego responde con el gráfico en línea

Datos con los que trabajar → tako_search en paralelo (sintetiza tú mismo):

1. El usuario pregunta: "Compara la inflación de IPC, IPC subyacente, PCE y PCE subyacente de EE. UU."
2. El agente lanza cuatro llamadas estrechas de tako_search simultáneamente — una por entidad y métrica
3. Cada una devuelve una tarjeta con valores destacados (el primer resultado se renderiza en línea como un gráfico)
4. El agente sintetiza los cuatro resultados, llamando a tako_contents en el url de una tarjeta si necesita filas completas (cuando la tarjeta es exportable: true)

Copia el bloque de abajo y pégalo en Claude Code. Configurará la conexión MCP y la habilidad por ti.

Step 1: Install or update Tako MCP

If Tako MCP already exists in your config, update it to this endpoint. Run this in your terminal:

claude mcp add tako-mcp --transport http "https://mcp.tako.com/mcp" --header "Authorization: Bearer $TAKO_API_TOKEN"


Step 2: Add this Claude skill

---
name: tako-financial-research
description: >-
  Use when the user asks what a company's financial metric is or was (revenue, margins, EPS, cash flow, valuation, stock price, analyst estimates), compares companies on a metric, asks who a company competes with or what data exists on it, or wants a financial chart — including private companies and crypto spot prices. Returns the figures as structured, citation-backed data from Tako (S&P Global, Fiscal.ai, Visible Alpha, Xignite and others), each with a chart. Company-level data only, not country indicators or website traffic.
---

# Financial Research (Tako)

Tako serves company financials as structured, cited data: each result is a card carrying the headline value, the underlying rows, and a chart of the series. All tools below live on the Tako MCP server installed in Step 1. The tool descriptions and every result already carry the card fields, the `sources` guidance and the zero-card recovery; this skill covers how to shape a financial query, how to check a card against the question, and how to report.

## Workflow

1. **Query as ENTITY + METRIC**: `"Nvidia revenue"`, `"Tesla free cash flow"`, with `quarterly` or `annual` to steer the period. When the user wants several metrics or companies, run one call per pair in parallel: each answer then comes back as its own card, and the checks below apply cleanly to each.
2. **Call `tako_search`** with the default sources. Web results carry the qualitative half and the facts the graph doesn't hold (earnings dates, management commentary, companies with no filings or coverage).
3. **Check the top card against the question** with the list below. The top card renders inline automatically; if a different card is the right one, link its title to its `url` and say so.
4. **Read the figure from the card's `description`.** Fetch the series with `tako_contents` on the card's `url` only when you need the rows, such as to compute a growth rate, ratio or change yourself: search retrieves reported values and derives nothing. A locked card (`exportable: false`) is a licensing wall, not an error: quote the headline and stop.
5. **Zero cards?** Follow the recovery the result states, and keep to two priced searches per question. Empty means Tako doesn't cover it, not that the fact is false: no dividend card is not "pays no dividend".
6. **Ambiguous entity?** `"Costco"` resolves to Costco Wholesale Corporation and Costco Wholesale Australia; `"Coca-Cola"` to four listed companies. If the user's intent doesn't settle it, ask before quoting a number.
7. **Discovery asks** ("who does Nvidia compete with", "what does Tako track for Tesla", "Nvidia's acquisitions")? Resolve the entity with `tako_available_data` to get its node id, then call `tako_graph_related` on it. The first call returns the relation map with counts (`rel:competes_with`, `rel:subsidiaries`, `rel:acquisitions`, `metrics`, `sources`); pass `relation` to page one and `q` to filter it, then search on the names it returns.

## Checking a card against the question

Search ranks on relevance to the words, and financial vocabulary is dense: the same query can match a level and a rate, a segment and the total, an actual and an estimate. Before quoting, confirm:

1. **Metric.** The title names the metric asked for, not an overview of several. Overview cards ("Earnings & Estimates Overview", "Ratios Overview", "Stock Overview") summarize many metrics and lead with estimate-vs-actual; use one only when the question is that broad.
2. **Scope.** The card is company-wide unless a segment or geography was asked for. Segment cards exist for every line the company reports, so they can match the same words. If only a segment card exists, say so; never pass a segment off as the total.
3. **Unit.** A rate query can match the level (operating income vs operating margin). Confirm the unit in `description`.
4. **Reported or estimate, as asked.** Analyst-estimate and consensus cards match plain metric queries, and a future `coverage_end` is how you spot one. Both are financial data: quote the estimate when the question is about forecasts or consensus and label it so; otherwise take the reported card.
5. **Entity.** `nodes` names the company asked about; related listed entities share names. Some cards (Fiscal.ai charts, Stock and Ratios Overviews) carry no nodes; fall back to the title there.

## Comparisons

- A two-series comparison card exists for many pairs but not all; some pairs return two single-entity cards. Treat a card as a comparison only if every compared entity appears in its `nodes` or title; otherwise synthesize from the per-entity cards. Comparisons default to annual; say `quarterly` for quarterly.
- A cross-currency pair plots both series on one axis unnormalized. State each currency and convert before comparing; never present the raw chart as like-for-like.
- Period labels are calendar-normalized (a September fiscal year-end shows as Dec 31). Flag the normalization when the fiscal period matters.

## Output

1. One or two lines on the finding, referencing the chart in prose. Never re-post the image URL: it double-renders the inline chart.
2. Source name and `coverage_end` date. Cite the source the card names; it varies by metric. Say plainly when a figure came from a web result rather than a card.
3. One `[Open in Tako](url)` link for the card you embedded.

Step 3: Ask the user to restart Claude Code

Ask the user to restart Claude Code so the config change takes effect.

Copia el bloque de abajo y pégalo en Claude Code. Configurará la conexión MCP y la habilidad por ti.

Step 1: Install or update Tako MCP

If Tako MCP already exists in your config, update it to this endpoint. Run this in your terminal:

claude mcp add tako-mcp --transport http "https://mcp.tako.com/mcp" --header "Authorization: Bearer $TAKO_API_TOKEN"


Step 2: Add this Claude skill

---
name: tako-web-traffic
description: >-
  Use when the user asks how much traffic a website gets, compares sites' visits, wants a top-sites ranking, asks which sites compete with a brand for attention, or asks about an app's monthly active users — including when they name the brand rather than the domain ("how much traffic does Netflix get"). Returns SimilarWeb figures as structured, citation-backed data from Tako, each with a chart. Not for company financials such as subscribers or revenue.
---

# Web & App Traffic (Tako)

Tako serves SimilarWeb traffic data as structured, cited data: each result is a card carrying the headline value and a chart of the series. All tools below live on the Tako MCP server installed in Step 1. The tool descriptions and every result already carry the card fields, the `sources` guidance and the zero-card recovery; this skill covers how to shape a traffic query, how to check a card against the question, and how to report.

## Workflow

1. **Query by domain**: `"netflix.com monthly visits"`, `"chatgpt.com"`. Traffic data is keyed by domain, so resolve a brand to its domain yourself. For app usage, query app name + metric: `"Spotify app monthly active users"`; app cards are keyed by the bare app name.
2. **Call `tako_search`** with the default sources. Web results add competitive write-ups and ranking roundups.
3. **Check the top card against the question** with the list below. You have the traffic number only when the card's title is `<domain> Monthly Visits`, or the app's active-users card.
4. **Read the figure from `description`**: the latest monthly value and the % change over the period. Traffic cards are licensed and don't export (`exportable: false`), so the description and the chart are the data; don't call `tako_contents` on one. Web-result urls remain fetchable.
5. **Zero cards?** If the query wasn't a bare domain, make it one and retry once. If a domain query is still empty, answer from the web results and label the figure web-sourced. Don't use `tako_available_data` to rule a domain out: the graph resolves brands to companies, not to domains, so a domain it doesn't know can still have a traffic card.
6. **Competitive asks** ("who competes with Netflix for attention", "Netflix vs its rivals")? Resolve the brand with `tako_available_data` to get its company node id, call `tako_graph_related` with `relation: "rel:competes_with"`, map the competitors to their domains yourself, and run one domain search per site in parallel.

## Checking a card against the question

1. **Domain, from the title.** Traffic cards list only the metric in `nodes`; the domain never appears there, so the entity check that works elsewhere doesn't apply.
2. **Absolute vs relative.** An `"A vs B"` card's description reports each series as a % change over the period. For absolute visits, read each domain's single-series card; run a per-domain search if the comparison result didn't include them.
3. **Ranking scope.** Ranking cards exist per category and per measure ("Top Websites by Visits", "Top Arts and Entertainment Websites by Visits", "… by Average Visit Duration"). The title names both; confirm they match the question.
4. **Metric family.** SimilarWeb app "Monthly Active Users" and a company's own reported MAU are different numbers from different sources, and both can appear in one result. Say which you're quoting.
5. **Month.** `coverage_end` is the data month. Cite it.

## Output

1. One or two lines on the traffic, referencing the inline chart in prose. Never re-post the image URL: it double-renders the chart.
2. "SimilarWeb" and the `coverage_end` month. Say plainly when a figure is web-sourced.
3. One `[Open in Tako](url)` link for the top card; point at extra cards by linking their titles to their `url`.

Step 3: Ask the user to restart Claude Code

Ask the user to restart Claude Code so the config change takes effect.

Copia el bloque de abajo y pégalo en Claude Code. Configurará la conexión MCP y la habilidad por ti.

Step 1: Install or update Tako MCP

If Tako MCP already exists in your config, update it to this endpoint. Run this in your terminal:

claude mcp add tako-mcp --transport http "https://mcp.tako.com/mcp" --header "Authorization: Bearer $TAKO_API_TOKEN"


Step 2: Add this Claude skill

---
name: tako-macroeconomics
description: >-
  Use when the user asks what a country's economic indicator is or was (inflation, CPI, PCE, unemployment, GDP, interest rates, population), compares countries on one, asks which indicators exist for a country or which countries belong to a bloc, or wants a macro chart or briefing. Returns the figures as structured, citation-backed data from Tako (FRED, BLS, OECD, BIS, IMF, World Bank, Census and Polymarket), each with a chart. Country-level indicators only, not company financials or website traffic.
---

# Macroeconomics (Tako)

Tako serves macro and demographic indicators as structured, cited data: each result is a card carrying the headline value, the underlying rows, and a chart of the series. All tools below live on the Tako MCP server installed in Step 1. The tool descriptions and every result already carry the card fields, the `sources` guidance and the zero-card recovery; this skill covers how to shape a macro query, how to check a card against the question, and how to report.

## Workflow

1. **Query as COUNTRY + INDICATOR**: `"US CPI inflation"`, `"Japan unemployment rate"`. Coverage is keyed by country. For a bloc or region, check coverage with `tako_available_data` before searching: member-country series are far denser, so aggregate them yourself or take the figure from the web results and say so.
2. **Name the variant when intent is precise.** Most indicators exist in several variants with materially different values: headline vs core, seasonally adjusted or not, BLS vs IMF vs OECD-harmonised, U-3 vs U-6, target rate vs effective rate. When you don't know the exact name, call `tako_available_data` first, which is free, and search on the name it returns. Level and rate series share a stem: "Core PCE Price Index" is the index level and "Core PCE Price Index (% Change)" is the inflation rate, and a query that says "inflation" can match either, or a CPI series.
3. **Call `tako_search`** with the default sources. Web results carry release commentary and cover the gaps in bloc-level data.
4. **Check the top card against the question** with the list below. If a different card is the right one, link its title to its `url` and say so.
5. **Read the value from `description`.** When the card is exportable and you need more than the headline, `tako_contents` on its `url` returns the series.
6. **Zero cards?** Follow the recovery the result states, and keep to two priced searches per question. Empty means not covered, not that the indicator doesn't exist.
7. **Discovery asks** ("what does Tako track for Japan", "which countries are in the G7", "who publishes Japan's data")? Resolve the country with `tako_available_data` to get its node id, then call `tako_graph_related` on it. The first call returns the relation map with counts (`metrics`, `part_of`, `siblings`, `sources`; `members` on a bloc node); pass `relation` to page one and `q` to filter it, then search on the names it returns.

## Checking a card against the question

One indicator name covers many series: providers, methodologies, vintages, levels and rates, and prediction markets on the same quantity. Before quoting, confirm:

1. **Variant.** The title names the variant asked for; several providers' headline numbers can come back together. Don't average them or take the first.
2. **Vintage, as asked.** For a current figure, take the series whose `coverage_end` is latest among the matches: discontinued series stay in the graph and an annual series can sit a year behind the monthly one. For a historical period, any series that covers it is valid. Series refresh on different schedules, so don't present two indicators as the same vintage without checking.
3. **Rate, not level.** A "(% Change)" card is a percentage; a bare "Price Index" card is index points. Confirm from the unit in `description`.
4. **Indicator or expectation, as asked.** Polymarket cards report what traders expect, not what a statistics agency published, and exist for many macro quantities. Quote one when the question is about expectations, and label it market-implied; otherwise take the published series.
5. **Country.** `nodes` names it. Country overview cards sometimes carry no nodes; fall back to the title there.

## Comparisons

- Cross-country comparison is built in: `"US vs China inflation"` returns a two-series card. For currency-denominated indicators (GDP, wages) the chart plots both currencies on one axis unnormalized; state each currency and convert before comparing.

## Output

1. One or two lines on the indicator, referencing the chart in prose. Never re-post the image URL: it double-renders the inline chart.
2. Source name and `coverage_end` date. The roster is wider than FRED, so cite what the card names. Say plainly when a figure is web-sourced.
3. One `[Open in Tako](url)` link for the card you embedded.

Step 3: Ask the user to restart Claude Code

Ask the user to restart Claude Code so the config change takes effect.

v0.3.0:

• La superficie de herramientas se reorganizó en un pequeño listado predeterminado más ?tools= opciones, y se introdujeron alias de grupo ?tools= (graph, credits, answer, visualize, agent). Tanto los alias como varias de esas herramientas han desaparecido — consulta la entrada anterior y docs/TOOLS.md para la superficie actual.
• Las herramientas de imagen de gráfico (get_chart_image), gráfico interactivo (open_chart_ui), creación de gráficos (create_chart) e informes (create_report, get_report, list_reports, export_report) se eliminaron.
• El servidor Python autoalojado (pip install tako-mcp / Docker) se eliminó en favor del Worker de Cloudflare alojado.

Actualiza cualquier configuración de cliente o indicaciones de agente que hagan referencia a los nombres de herramientas antiguos o al endpoint SSE de Python.

Tako se publica en el Registro MCP oficial como servidor remoto bajo io.github.TakoData/tako-mcp.

• server.json (raíz del repositorio) es el descriptor del registro: una entrada remota streamable-http que apunta a https://mcp.tako.com/mcp. El esquema no lista herramientas: los hosts las descubren en tiempo de ejecución a través de tools/list. (Distinto de registry/server.json, el catálogo de herramientas generado en el repositorio usado por npm run registry:gen / registry:check.)
• Publicación está automatizada por .github/workflows/publish-mcp.yml, autenticando a través de GitHub OIDC (sin secreto). La versión vive en el código: sube el version de server.json, fusiona a main, y se publica automáticamente. Una fusión que no cambia la versión es una no operación.
• Espacio de nombres de marca (com.tako/tako-mcp) es una mejora futura que requiere autenticación DNS (clave Ed25519 + registro TXT en tako.com).
• Versionado y registro de cambios están automatizados a través de release-please. Los contribuyentes usan títulos de PR de Conventional Commit (fusión squash); los mantenedores cortan un lanzamiento fusionando el PR release: X.Y.Z del bot. Consulta AGENTS.md → Lanzamientos.