# Tako (remote · mcp.tako.com)

Give your agent web search and authoritative datasets: S&P Global, FRED, OECD, SimilarWeb & more.

- Trust score: 68/100 (medium)
- Change this week: +45
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.tako.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/takodata-tako-mcp/mcp.md), [page](https://verifymcp.io/servers/takodata-tako-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.tako.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.16.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 52/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3113 tokens (~1037/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

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

### Codex

```toml
[mcp_servers.takodata-tako-mcp]
url = "https://mcp.tako.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "takodata-tako-mcp": {
      "type": "remote",
      "url": "https://mcp.tako.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add takodata-tako-mcp --url https://mcp.tako.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  takodata-tako-mcp:
    url: "https://mcp.tako.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "takodata-tako-mcp": {
      "type": "http",
      "url": "https://mcp.tako.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 67, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 64, +1)

- [functional] MCP protocol: Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server
- [functional] Server version: 0.15.1 → 0.15.3

### 2026-07-30 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-29 (score 62, 0)

- [security] Tool “tako_answer” rewrote its description, which is the text the model reads
- [security] Tool “tako_available_data” rewrote its description, which is the text the model reads
- [security] Tool “tako_search” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 633 → 904
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.14.0 → 0.15.0
- [cosmetic] “tako_answer” added an optional parameter “include_contents”
- [cosmetic] “tako_answer” added an optional parameter “preview_rows”
- [cosmetic] “tako_available_data” added an optional parameter “coverage_filter”
- [cosmetic] “tako_search” added an optional parameter “preview_rows”
- [cosmetic] “tako_available_data” reworded the description of “q”
- [cosmetic] “tako_search” reworded the description of “include_contents”

### 2026-07-28 (score 62, +39)

- [security regression] Authorization: pass → partial
- [security improvement] Transport: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100

### 2026-07-27 (score 23, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 23)

First indexed and scored.

## MCP tools (3)

### `tako_answer` (~886 tokens)

Tako: Answer

START HERE for any question that wants a value, figure, or finding: ask one specific data question, get one synthesized answer grounded in the data or web tako cites.

It is the only tool whose single response can finish the job: it reads the cited pages internally, inlines the cited cards' rows, and returns a coverage verdict. Retrieval hands back captions and links you must then chase, and every extra round trip re-sends the whole conversation.

Best for: a single, self-contained data question with one answer. The `answer` is synthesized from the cited sources; the `cards` are its citations. Also the values channel for non-exportable cards: when a card is `exportable: false` (usually license-gated), ask here with its METRIC node id pinned and strict:true to get the figures.

Reach past it only for a different job: `tako_search` for breadth recon and chart cards (it locates data, it does not carry values), `tako_available_data` when the question is what Tako covers, the Answer Agent for open-ended research.

Grounds over BOTH data and web by default. Run `tako_available_data` first when unsure the data exists — pass `metric` to get the entity+metric pair — then pin the METRIC node id it returns, with strict:true (an entity-only pin, or a pin without strict, does not steer retrieval). Cited cards inline their recent rows (see include_contents/preview_rows), so the series arrives with the answer; for full history or a cited page's text, call `tako_contents` on its url.

Results arrive as markdown: the synthesized answer first, then its cited data cards (headline, exportable flag, node ids, a rows-count pointer) and web citations, then source notes. The cited cards' actual rows ride in structuredContent (cards[].content), not the markdown, alongside machine essentials (request_id, usage, guidance).

Input parameters:

- `country_code` (string): ISO country code for localized results.
- `include_contents` (boolean): Inline each cited data card's recent rows alongside the answer (default true; preview_rows sets how many) — the values arrive with the prose, no follow-up fetch. Set false — prose + citations only —…
- `locale` (string): Locale for results.
- `node_ids` (array): Graph node ids (from tako_available_data) to PIN into the proprietary data source. Pinned nodes get a strong retrieval boost. Max 20. Applies only to the 'data' source.
- `preview_rows` (integer): Cap on the rows of each cited card's data inlined when include_contents is true — always the N MOST-RECENT rows (default 20, the free inline allowance the server ships; values above your account's al…
- `query` (string, required): Natural-language question to answer (e.g. "What was US GDP in 2024?"). Website-traffic data is keyed by domain — ask about "openai.com monthly visits", not "OpenAI website visits".
- `sources` (array): Source(s) to ground in. Default ["data","web"] (both) — keep BOTH enabled unless you have a confirmed reason to narrow. Narrow to ["data"] only once `tako_available_data` has confirmed the proprietar…
- `strict` (boolean): Hard filter. When true, return ONLY cards matching at least one node in node_ids (which must then be non-empty — empty node_ids + strict is a 400). When false (default), pinned nodes are preferred/bo…

Output parameters:

- `answer` (string): The synthesized, citation-backed answer.
- `cards` (array): Cards cited by the answer.
- `guidance` (string): Present only when the data source grounded zero cards: the deterministic coverage verdict.
- `request_id` (string)
- `usage`: Cost-plus usage for this request (null when not metered).
- `web_results` (array): Web results cited by the answer.

### `tako_available_data` (~716 tokens)

Tako: Available Data

Find what proprietary, continuously-updated structured data exists on something — summarized in one call. Free and fast.

Ask it when the question IS coverage: what does Tako have on X, is this measure tracked at all, what is it called. Then build the real question around what comes back. NOT a required first step — for a straightforward data question, tako_search or tako_answer directly is usually right.

Worth one call first when you need a measure's EXACT name: resolving a loose phrase to the canonical metric name measurably improves what the priced call retrieves (measured, 9 of 15 pairs).

Works on an entity (a company, person, or place → the metrics tracked on it, e.g. Tesla) or a metric (→ the entities it is tracked across, e.g. Inflation Rate).

Tips:
Know the measure? Split it: q="Carnival", metric="passenger cruise days" — you get the entity+metric pair and a runnable next_call in ~0.6s. Only omit `metric` to browse everything an entity has.
One metric across many entities → one metric-first call; one entity across many metrics → one entity-first call. The returned coverage list answers all of them at once — never loop one call per name.
Pass `label` when you can categorize the term (company → ORG, country → GPE, person → PERSON).
Each match lists the exact metric/entity names, and structuredContent.matches[].coverage.items[] pairs each name with its node id. To land on exactly one metric, pin THAT node id alone with strict:true and name the entity in the query text; the call then returns that metric's card or nothing. When the measure is known — you passed `metric`, or `q` named a metric — `next_call` is that follow-up prewritten (query + the metric node + strict) — run it verbatim.
A broad entity's coverage list is capped, so it can be truncated: treat a name you don't see as UNCONFIRMED rather than absent, and fall back to the web instead of re-calling this tool to double-check.
This tool confirms a name EXISTS in the graph; it cannot confirm a chart e…

Input parameters:

- `label` (string): NER label to prefer for `q` (boost, not a filter). Supply when you can categorize the term (company→ORG, place→GPE, person→PERSON, ...). Describes the ENTITY only — it is not applied to `metric`.
- `metric` (string): The measure you want, when you already know it — e.g. "gross margin", "passenger cruise days", "capex". Supplying it is the FAST path: the tool resolves the entity+metric pair directly and hands back…
- `q` (string, required): The NAME of the entity (or metric) to look up, min 2 chars — e.g. "Carnival", "United States", "Nvidia". Put the measure in `metric`, not here.
- `types` (string): Narrow resolution to a "thing" ("entity") or a "measure" ("metric"). Omit to search both.

Output parameters:

- `entity`
- `entity_alternates` (array)
- `found` (boolean): True when at least one match has live data coverage — not mere node resolution.
- `matches` (array): The resolved matches and their coverage, each entry carrying the node id to pin. To fetch a specific metric precisely: call tako_search or tako_answer with node_ids=[<the metric's node_id>] AND stric…
- `metric`: The metric whose node_id belongs in the follow-up's node_ids.
- `metric_alternates` (array): Runners-up. The top metric is right ~80% of the time and the top three ~93-95%, so check these before accepting the primary.
- `metric_query` (string)
- `next_call`: Ready-to-run follow-up: call this tool with exactly this query, node_ids and strict. node_ids holds the METRIC node only — strict is an OR over pinned nodes, so adding the entity id widens the filter…
- `query` (string)

### `tako_search` (~1238 tokens)

Tako: Search

Reconnaissance and chart retrieval across the live web and proprietary data: many results at once, returned as structured cards and web links, and the top card auto-renders inline as a chart.

It locates data — and for `exportable: true` cards it also includes a free 20-row preview by default (`include_contents`) — but a license-gated card carries no rows at all (headline value only, via `description`), and a web result is only a snippet, not a value. For a plain "what is X", `tako_answer` is the better-suited tool: one written figure beats parsing a preview table yourself, and reaching here first for that costs an extra round trip that re-sends the whole conversation. To ask it about a card you already have, pin that card's METRIC node id ALONE (the `mt::` entry in its `nodes`) with strict:true — pinning every node id on the card, or omitting strict, does not steer retrieval.

Best for: breadth — fanning out many narrow queries in parallel to see what exists across several entities or metrics; retrieving a chart card when the chart or embed is itself the deliverable; and harvesting node ids and urls to feed `tako_answer` or `tako_contents`. It is cheap and fast, and built for exactly this fan-out.

Coverage spans economics, finance, company KPIs, demographics, sports, markets, weather, elections, prediction markets, website/app traffic, real estate, energy, health, and more — metrics that sound web-only (e.g. SimilarWeb-style website traffic) are in the data graph.

Each query resolves one entity + one metric ("Apple revenue", "Nvidia vs AMD gross margin"); broad or compound queries ("today's sports + odds") retrieve poorly. When the question is what Tako covers, or you need a metric's exact name, run `tako_available_data` (free) instead of guessing here.

Data and web come back together — treat them as one result, not an either/or. Returns: `cards` (up to `count`) with preview rows and chart URLs, plus `web_results`. To read a web result in full, call `tako_conte…

Input parameters:

- `count` (integer): Maximum number of results to return per source (1-20).
- `country_code` (string): ISO country code for localized results.
- `effort` (string): Search effort: "fast" (default) or "instant" (fastest, serves cached embeds as-is). Omit for fast.
- `include_contents` (boolean): Inline each Tako card's data preview (default true; preview_rows sets how many rows). Set false — pointers-only, no rows — for large parallel fan-outs or when coverage is unconfirmed (no prior tako_a…
- `locale` (string): Locale for results.
- `node_ids` (array): Graph node ids (from tako_available_data, or a card's nodes) to PIN into the proprietary data source. Pinned nodes get a strong retrieval boost. Max 20. Applies only to the 'data' source.
- `preview_rows` (integer): Cap on the rows of each card's data inlined when include_contents is true — always the N MOST-RECENT rows (default 20, the free inline allowance the server ships; values above your account's allowanc…
- `query` (string, required): Natural-language search query (e.g. "US GDP growth", "Intel vs Nvidia revenue"). Website-traffic data is keyed by domain — query "openai.com monthly visits", not "OpenAI website visits".
- `sources` (array): Source(s) to search. Default ["data","web"] (both) — keep BOTH enabled unless you have a confirmed reason to narrow. Narrow to ["data"] only once `tako_available_data` has confirmed the proprietary d…
- `strict` (boolean): Hard filter. When true, return ONLY cards matching at least one node in node_ids (which must then be non-empty — empty node_ids + strict is a 400). When false (default), pinned nodes are preferred/bo…

Output parameters:

- `cards` (array): The data cards — the payload. Each carries its title, description (headline value), facts, and inline rows under `content`.
- `dark_mode` (boolean)
- `embed_url` (string)
- `guidance` (string): Present only on a zero-card response: the recovery protocol.
- `height` (integer)
- `image_url` (string)
- `pub_id` (string)
- `request_id` (string)
- `usage`: Cost-plus usage for this request (null when not metered).
- `web_results` (array): Web results with their snippets.
- `width` (integer)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/takodata-tako-mcp/mcp#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 68
- 2026-08-01: 67
- 2026-07-31: 64
- 2026-07-30: 63
- 2026-07-29: 62
- 2026-07-28: 62
- 2026-07-27: 23
- 2026-07-26: 23

## Links

- Remote endpoint: https://mcp.tako.com/mcp
- Repository: https://github.com/TakoData/tako-mcp
- Changelog RSS feed: https://verifymcp.io/servers/takodata-tako-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/takodata-tako-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/takodata-tako-mcp/mcp