Tako

插件（推荐）——一步即可安装 MCP 连接以及 Tako 内置的查询与研究技能，并且可立即使用免费套餐——无需生成或管理 API 密钥：

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

就这样——tako_search 可立即在匿名免费套餐中使用。若要解锁完整工具集并使用你自己的账户限额，请通过 OAuth 进行一次身份验证：在 Claude Code 中运行 /mcp，选择 tako，然后选择 Authenticate。浏览器会打开，让你使用 Tako 账户登录，并自动为你生成一个针对当前主机的 API 密钥（可在 tako.com/console/api-keys 查看和撤销）。同一 OAuth 流程也支持 Claude.ai 上的插件——只需点击一下，插件的 Tako 连接器即可连接，无需粘贴令牌。

如果你之前使用 claude mcp add 添加过该服务，请先将其移除（claude mcp remove tako-mcp），以免每个工具都出现两个副本。

从较早版本的插件更新？ 旧版本要求在插件配置中填写 Tako API 密钥；此设置现已移除，因此更新后你的连接会悄然切换到匿名套餐（tako_search 可以运行；其他工具会要求你登录）——不会报错，但你的账户限额将不再生效。运行一次 /mcp → tako → Authenticate（或使用 Claude.ai 上的 Connect 按钮）即可恢复完整的已验证访问权限。

或者直接添加 MCP 服务（然后通过 /mcp → tako → Authenticate 就地完成身份验证）：

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

运行 claude mcp list（应显示 tako 已连接）或在会话中运行 /mcp 进行验证。

使用上方的一键安装徽章，或将配置添加到 ~/.cursor/mcp.json——Cursor 会在首次使用时提示你登录：

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

将配置添加到 Windsurf MCP 配置中——Windsurf 会在首次使用时提示你登录：

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

将配置添加到 .vscode/mcp.json（工作区）或你的用户 mcp.json 中——VS Code 会在首次使用时提示你登录：

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

**扩展（推荐）**只需一条命令即可安装，并且可立即使用免费套餐，无需生成或管理 API 密钥：

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

这会安装 MCP 连接、Tako 内置的查询与研究技能，以及三个命令：

要解锁完整工具集和你自己的账户限额，请先进行一次身份验证：在 Gemini CLI 中运行 /mcp auth tako。浏览器会打开，让你使用 Tako 账户登录，并自动为你生成一个按主机分配的 API 密钥（可在 tako.com/console/api-keys 查看并撤销）。

手动配置：如果你不想安装扩展，或想固定 ?tools= 允许列表，请在 ~/.gemini/settings.json 中添加以下内容（之后使用 /mcp auth tako 进行身份验证）：

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

若要改用 API 密钥，请添加一个包含 "Authorization": "Bearer <key>" 的 headers 区块——但必须填写完整：Gemini 会将未设置的 ${VAR} 引用按原样替换，而格式错误的 Authorization 标头会被拒绝而非忽略，因此，填写不完整的令牌会导致连接失败；完全不提供令牌反而可以正常连接。

添加到 opencode.json 中——首次使用时，OpenCode 会提示你登录：

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

Codex 通过 mcp-remote 桥接程序连接远程服务；首次连接时，该程序会在浏览器中启动登录流程：

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

添加到 Zed settings.json 中（通过 mcp-remote 桥接程序；首次连接时，该程序会在浏览器中启动登录流程）：

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

面向消费者的聊天平台不接受 Bearer 令牌。claude_desktop_config.json 只会验证 stdio 服务，因此其中的远程 "type": "http" 条目会被静默丢弃——Claude Desktop 通过 Connectors 连接，和 Claude.ai 一样。托管端点会运行 OAuth 2.1 流程，让你使用 Tako 账户登录，并自动为你生成一个按主机分配的密钥。

前提条件：只需使用你要授权的身份登录 tako.com。你无需自行生成令牌——授权流程会创建一个按主机分配的密钥（名称为 MCP: <client>，可在 tako.com/console/api-keys 查看并撤销）。连接新主机不会轮换其他主机的密钥；超过十个 MCP 密钥时，Tako 会删除最旧的密钥。

Claude.ai (需要 Pro、Max、Team 或 Enterprise)

1. 打开 Claude.ai → Settings → Connectors
2. 点击 Add custom connector
3. 粘贴 https://mcp.tako.com/mcp，然后点击 Connect
4. 完成 Tako 登录流程；随后 Tako 会显示为已连接

Claude Desktop (计划要求与 Claude.ai 相同)

1. 打开 Claude Desktop → Settings → Connectors
2. 点击 Add custom connector
3. 粘贴 https://mcp.tako.com/mcp，然后点击 Connect
4. 完成 Tako 登录流程；随后 Tako 会显示为已连接

ChatGPT — 从 ChatGPT 的应用目录安装 Tako 应用（它通过 OAuth 连接，并使用 https://mcp.tako.com/mcp/chatgpt 应用端点）。若要手动将其添加为自定义连接器 (需要 Pro、Business 或 Enterprise，并启用 Developer Mode)：

1. 打开 ChatGPT → Settings → Connectors → Developer Mode，并将其开启
2. 点击 Create custom connector
3. 粘贴 https://mcp.tako.com/mcp/chatgpt，然后点击 Connect
4. 完成 Tako 登录流程；随后连接器会显示在列表中并可供使用 /mcp/chatgpt 端点仅支持 OAuth，并针对 ChatGPT 进行了优化（交互式图表小组件、固定列出 7 个工具；其中会忽略 ?tools=）。通用 /mcp URL 在那里也能使用。只有在 initialize 中声明支持 MCP Apps 的客户端才会收到图表小组件；其他客户端会收到图表图像。

连接期间，无论使用哪个宿主，你都会看到 3 个由 Tako 托管的页面：登录页面（使用 Google，或你的 Tako 邮箱和密码）、授权页面（“将 [host] 连接到 Tako — 允许 / 取消”），然后跳转回宿主。宿主也可能显示自己的授权提示——这是正常的。

断开连接。 在某个宿主中断开连接（在宿主设置中移除连接器）只会停止该宿主；其他宿主和使用 Bearer 身份验证的客户端仍可继续使用。若要彻底终止所有连接，请在 tako.com/console/api-keys 轮换密钥——所有宿主上先前签发的授权都会立即无法通过身份验证。

两个工具，前后衔接 — tako_search 负责查找，tako_contents 负责获取：

• 宽泛或包含多个部分的问题 → 并行执行多个范围较窄的搜索。 将问题拆解为单个实体 + 指标的查询，并发执行 — 例如 “美国 CPI 通胀”、“美国核心 CPI 通胀”、“美国 PCE 通胀” — 然后自行综合结果。
• 询问 Tako 覆盖哪些内容 → 使用 tako_available_data。 它会返回指标的准确名称；即使未找到，仍可进行网页搜索。

具体问题 → 搜索，然后获取数据行：

1. 用户提问：“2024 年美国 GDP 是多少？”
2. Agent 调用 tako_search；排名靠前的卡片会显示标题值及其图表
3. 如需获取完整数据序列，Agent 会对该卡片的 url 调用 tako_contents，然后以内联图表形式作答

需要处理的数据 → 并行调用 tako_search（自行综合结果）：

1. 用户提问：“比较美国 CPI、核心 CPI、PCE 和核心 PCE 通胀。”
2. Agent 并发执行 四 个范围较窄的 tako_search 调用，每个调用对应一个实体 + 指标
3. 每次调用都会返回一张包含标题值的卡片（在 ChatGPT 应用以及声明支持 MCP Apps 的其他宿主中，每张卡片都会渲染为图表；在其他地方则会渲染第一张卡片的图表）
4. Agent 综合四项结果；如果需要完整数据行（且卡片的 exportable: true），则对卡片的 url 调用 tako_contents

复制下面的代码块并粘贴到 Claude Code。它会为你设置 MCP 连接和技能。

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?tools=search,available_data,contents,graph_related,agent,company_agent,visualize" --header "Authorization: Bearer $TAKO_API_TOKEN"


Step 2: Add this Claude skill

---
name: tako-search
description: >-
  Use when you need to look something up: current events, facts, figures, or pages on any topic. Also use it when the answer needs a calculation over real-world data. Tako searches the web and a knowledge graph of licensed data in one call, and returns web results, plus a structured, cited card when the graph has one.
---

# Tako

Tako searches the web and a knowledge graph of licensed and public data in one call. The graph covers companies, business professionals, markets, economies, sports, weather, prediction markets, websites, and more, and refreshes much of it during the day. When the graph has the answer, the result leads with a card: a headline value, its source, and a chart. Every search also returns web results. All tools below live on the Tako MCP server installed in Step 1.

## Look something up

1. Search first. Call `tako_search` once per question, naming the entity and what you want: "Apple revenue", "Lakers last game score", "US CPI inflation", "EU AI Act timeline". For a comparison, name both entities in one query: "Nvidia vs AMD gross margin". Run independent searches in parallel.
2. Query website traffic by domain: "netflix.com monthly visits", not "Netflix website visits".
3. If a card comes back, check that it answers the question: the same entity, metric, and unit. For example, operating income isn't operating margin. Read the value from the card's `description`. To compute something from the card's rows, such as a growth rate, an average, or a correlation, follow **Compute over a series**.
4. If no card answers the question, answer from the web results. To read a page in full, pass its url to `tako_contents`.
5. If a name is ambiguous, such as "Costco" or "Coca-Cola", and the question doesn't settle which entity, ask before quoting a number.

If the user asks for Tako's agent and the `tako-agent` skill is installed, follow `tako-agent` instead.

## Find professionals and companies

`tako_search` finds business professionals and companies for B2B research, prospecting, and recruiting, and returns them as a list card. Each row is one professional or company, with their title, employer, location, LinkedIn, and a `tako_url` to their own page. Use it when the user wants the professionals or companies themselves: a list of prospects or candidates, or the professional record of someone they name.

**Professionals by role and place.** Name who and where.

- Who: a role or title ("engineers", "CFO", "VPs of sales", "head of marketing", "founders", "interns"), or a word for a company's people ("employees", "staff", "leadership team"). "Executives", "leadership", and "management" return C-suite and VP-level people.
- Where: an employer, a place, or both: "engineers at Stripe", "CFOs in Austin", "engineers at Google in London". A place needs a role, so "people in Austin" returns no list. A role alone ("CFOs") and an employer alone ("Stripe") also return no list.
- To find who holds a role at one company, search the role and the company: "Airbnb CFO" or "who is the CFO of Airbnb".
- Give a city its state or country: "engineers in Portland, OR". A bare city name matches every place with that name.

**A professional by name.** Search the full name alone, such as "Jane Doe". The list holds everyone with that name.

- Leave out everything else the user told you, such as the employer or title. Search reads every word as part of the name, so "Jane Doe Stripe" returns no list. Use those details to pick the person from the rows.
- Search doesn't match nicknames: "Tim Cook" and "Timothy Cook" return different people. If no row fits, try the other form of the name.
- A common name can match hundreds of people, and the rows can't be filtered by employer. If the person isn't in the first rows, fetch more and match on employer, title, and location.

**Companies by industry or type**, plus a place, a size, a funding stage, public or private, or a founding year: "fintechs in London", "SaaS companies with 50–500 employees", "Series B startups in Berlin", "AI startups founded since 2020".

Then read the list:

1. The card's `description` doesn't name the matches. To see them, pass the card's url to `tako_contents` with `max_rows` set to the rows the answer needs, such as 25. Fetch the full list, up to 1,000 rows, only when the user asks for it.
2. Check each row before you use it. A name list holds everyone with that name, and a company name can match more than one company. If more than one row fits the person the user means, ask which one.
3. Each row's `tako_url` opens that one person or company in Tako. Link it.
4. Tako withholds premium cells, such as business contact fields. A list card shows each one as 🔒, and the result's `note` names the withheld columns. Don't tell the user that a withheld field is empty. When the user asks for those fields, call `tako_contents` again with `premium: true`, and set `offset` and `max_rows` to only the rows they want, because Tako bills each of those rows. The row order can change between calls, so check the name on each row you get. After a `premium: true` call, the card's page shows those cells to anyone who opens it, so don't link that card unless the user wants to share them.
5. A list can't filter on revenue, investors, registry status, or a company's officers and directors. If the question needs one of those, say so. If the `tako-agent` skill is installed, offer Tako's company agent.
6. If no list card comes back, tell the user that Tako found no list. If the `tako-agent` skill is installed, offer Tako's company agent.

## Compute over a series

Compute in code, never in your head: growth rates, averages, CAGR, correlations, and rankings. Report what the code prints. Only a card marked `exportable: true` has rows to fetch.

1. **If you can run shell commands**, call `tako_contents` with `delivery: "link"`, then download the file right away: `curl -sfL -o <name>.csv "<url>"`. The link expires 5 minutes after the call. Analyze the file in a script and read only the result, so the rows never enter your context. If the result says `truncated`, call again with a higher `max_rows`, up to 100,000.
2. **If the download fails**, your shell may have no network access. Call `tako_contents` again without `delivery`, with `max_rows` at 2,000 or less, and pass the inline rows to your code tool.
3. **If you have no shell**, or `tako_contents` has no `delivery` input, fetch the rows inline and pass them to your code tool. With no code tool at all, show each step of the arithmetic so the user can check it.
4. **If `tako_contents` has a `format` input**, set `format: "card"` for a card's own structure, such as a company card's tabs.

## Explore what Tako has

For questions about coverage or relationships, such as "What does Tako track for Tesla?", "Who competes with Nvidia?", or "Which countries are in the G7?", resolve the entity with `tako_available_data`. Then call `tako_graph_related` on the node id it returns.

## Report

- Lead with the answer in one or two lines. The top card renders inline as a chart, so refer to it in prose; don't re-post its image URL.
- Name the source: the card's `source`, or the web page you used.
- Link the card you used: `[Open in Tako](url)`.
- If the series ended well before today, give its as-of date from `coverage_end`.

Step 3: Ask the user to restart Claude Code

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

复制下面的代码块并粘贴到 Claude Code。它会为你设置 MCP 连接和技能。

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?tools=search,available_data,contents,graph_related,agent,company_agent,visualize" --header "Authorization: Bearer $TAKO_API_TOKEN"


Step 2: Add this Claude skill

---
name: tako-agent
description: >-
  Use when the user explicitly asks for Tako's research agent or for deep, multi-step research with Tako, such as "use the Tako agent to…", "have Tako research…", or "use Tako's company agent to…". Tako's agents plan the steps, search the web and licensed data, and return a cited answer with charts or lists. For any other question, use tako-search, even one that needs a ranking or a calculation.
---

# Tako agents

Tako's agents run multi-step research. An agent plans its own steps, searches the web and Tako's licensed data, computes what the question asks for, and returns a cited answer with charts or lists. All tools below live on the Tako MCP server installed in Step 1.

## When to use an agent

Start an agent only when the user asks for one: they name Tako's agent or ask for deep or multi-step research with Tako. Otherwise, use `tako-search`, even when the question needs a ranking, a trend, a calculation, or a list of companies or professionals. Don't start an agent for a task that needs no data, such as writing, editing, or explaining a concept.

## Choose the agent

- Use `tako_company_agent` when the user names the Company Agent or wants a list of companies or of the professionals at them: companies by location, industry, status, founding date, funding, or size, or the officers, directors, executives, or employees of those companies.
- Use `tako_agent` for anything else, such as a chart, a written finding, or a ranking of companies by a metric.

## Run an agent

1. Send the user's question in `query`, one question per call. The agent plans its own steps, so don't split the question.
2. If `status` is `running`, call the same tool again with that `run_id` and no `query`. Don't start a new run for the same question.
3. If a call fails before it returns a `run_id`, follow its guidance. If the guidance says the run may have started, ask the user before you retry.
4. For a follow-up in the same conversation, pass the `thread_id` from the earlier run with the new `query`.

## Effort

`tako_company_agent` takes `effort`. Leave it unset for the default, `medium`. Use `high` only when the user asks for a thorough answer. Don't use `low` when the question filters by a financial metric such as revenue or headcount, because `low` can't. A thread keeps its effort, so omit `effort` on a follow-up.

## Report

- Lead with the agent's answer in a few lines, and keep its numbered citations.
- Link each card the agent returns: `[Open in Tako](url)`. The full chart or list lives on that page.
- If the agent says it couldn't answer part of the question, say so.

Step 3: Ask the user to restart Claude Code

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

• 工具接口已重组为精简的默认列表，并新增了 ?tools= 选择加入功能和 ?tools= 分组别名（graph、credits、answer、visualize、agent）。这些别名以及其中若干工具现已移除——请参阅上文条目和 docs/TOOLS.md，了解当前接口。
• 图表图片（get_chart_image）、交互式图表（open_chart_ui）、图表创建（create_chart）和报告工具（create_report、get_report、list_reports、export_report）已移除。
• 可自托管的 Python 服务（pip install tako-mcp / Docker）已移除，改用托管的 Cloudflare Worker。

请更新引用了旧工具名称或 Python SSE 端点的客户端配置或 Agent 提示词。

Tako 已作为远程服务发布到官方 MCP Registry，名称为 io.github.TakoData/tako-mcp。

• server.json（仓库根目录）是 Registry 描述文件：一个指向 https://mcp.tako.com/mcp 的远程 streamable-http 条目。架构不列出工具——主机在运行时通过 tools/list 发现工具。（这与 registry/server.json 不同，后者是仓库内生成的工具目录，由 npm run registry:gen / registry:check 使用。）
• 发布由 .github/workflows/publish-mcp.yml 自动完成，并通过 GitHub OIDC 进行身份验证（无需密钥）。版本号保存在代码中：更新 server.json 的 version，合并到 main 后便会自动发布。合并内容未更改版本号时，不会执行任何操作。
• 品牌命名空间（com.tako/tako-mcp） 是未来的升级，需要通过 DNS 进行身份验证（Ed25519 密钥 + tako.com 上的 TXT 记录）。
• 版本管理与变更日志通过 release-please 自动完成。贡献者使用 Conventional Commit 格式的 PR 标题（压缩合并）；维护者通过合并机器人创建的 release: X.Y.Z PR 来发布。请参阅 AGENTS.md → Releases。