# DataSnack (remote · datasnack.ai)

Seven-day forecasts of real-world numbers, linked and graded daily; sign-in adds Excel exports.

- Trust score: 38/100 (low)
- Change this week: −33
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `datasnack.ai`: 38/100 (this document), [markdown](https://verifymcp.io/servers/ai-datasnack-datasnack/datasnack.md), [page](https://verifymcp.io/servers/ai-datasnack-datasnack/datasnack)
- remote · `datasnack.ai`: 25/100, [markdown](https://verifymcp.io/servers/ai-datasnack-datasnack/mcp-public.md), [page](https://verifymcp.io/servers/ai-datasnack-datasnack/mcp-public)

## Channel facts

- Endpoint: `https://datasnack.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.3.0`

## 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 2026-11-21.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Tool Safety**: 0/100
  - Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 6 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the DataSnack MCP server?

DataSnack is a hosted endpoint at https://datasnack.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-datasnack-datasnack 'https://datasnack.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-datasnack-datasnack": {
      "url": "https://datasnack.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-datasnack-datasnack": {
      "type": "http",
      "url": "https://datasnack.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-datasnack-datasnack]
url = "https://datasnack.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-datasnack-datasnack --url 'https://datasnack.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-datasnack-datasnack:
    url: "https://datasnack.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-datasnack-datasnack": {
      "Transport": "http",
      "Url": "https://datasnack.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-datasnack-datasnack -t streamable-http -u 'https://datasnack.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-datasnack-datasnack": {
      "type": "http",
      "url": "https://datasnack.ai/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.

### 2026-11-21 (score 38, +2)

- [security improvement] Authorization: fail → pass
- [security] First check of Authorization: partial

### 2026-11-20 (score 36, +3)

- [security improvement] HSTS header: fail → pass

### 2026-11-18 (score 33, +10)

- [security regression] Endpoint reachability: not serving MCP → behind authorisation
- [security regression] Authorization: unverified → fail
- [security regression] Transport: fail → unverified
- [security] Tool safety: Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- [functional] Tool coverage: Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- [functional] Schema quality: Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- [functional] Capabilities: Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

### 2026-11-15 (score 23, −48)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Stability: 0.13 → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-11-14 (score 71, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1380 → 1574
- [functional improvement] Tool coverage: 43% → 48%
- [functional] Server version: datasnack-business-20261112160907-c04ed02 → datasnack-business-20261114010334-8cc3644
- [functional] New tool “questions”
- [functional] New tool “get_question”

### 2026-11-13 (score 71, +1)

- [functional] Server version: datasnack-business-20261111224909-f310cb2 → datasnack-business-20261112160907-c04ed02

### 2026-11-12 (score 70, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1230 → 1380
- [functional] Server version: datasnack-business-20261110234705-a535175 → datasnack-business-20261111224909-f310cb2
- [functional] New tool “head_to_head”

### 2026-11-11 (score 70, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1031 → 1230
- [functional improvement] Tool coverage: 73% → 79%
- [functional improvement] Tool coverage: 33% → 40%
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: datasnack-business-20261110192543-8741f90 → datasnack-business-20261110234705-a535175
- [functional] New tool “world”
- [functional] New tool “world_scenario”

## MCP tools (23)

### `search_models` (~81 tokens)

Search DataSnack models

Search DataSnack's public forecasting models of prediction-market questions. Each result gives the question, the market's number now (and which market it comes from), DataSnack's forecast for seven days from now, and the model's page.

Input parameters:

- `limit` (integer)
- `query` (string, required): Words to search for, such as a topic or a question

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `get_model` (~84 tokens)

Read a DataSnack model

Read one DataSnack model: the question, the market's number now, the model's forecast for seven days from now, how the model works, its sources and its graded record including misses.

Input parameters:

- `id` (string, required): A model id (such as ch:5eed0a7e11a0) or a https://datasnack.ai/m/... page URL

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `world` (~89 tokens)

The World Machine

DataSnack's World Machine: models of real-world numbers (fuel and food prices, freight, yields and mortgage rates, shipping, currencies, AI model ratings, company value), each predicting its number in seven days, with each model's record against standing still, the models it reads and that read it, and the scorecard.

Input parameters:

- `domain` (string): Optional: energy, rates, trade or ai

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `head_to_head` (~98 tokens)

DataSnack head to head

DataSnack's numbers beside big forecasters' published numbers for the same months, each made the day before theirs from public data, prediction markets and the news, and graded the same way. The equation and the record download as a spreadsheet.

Input parameters:

- `target` (string): Optional: one price (brent, wti, henry-hub, gasoline, diesel, brent-future, wti-future); omitted, the board

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `questions` (~45 tokens)

DataSnack questions

Odd questions about everyday costs, each answered by a calculation that runs on DataSnack's live models, with the answer now and in seven days, the working, the sources and the record.

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `get_question` (~123 tokens)

Read a DataSnack question

One of DataSnack's questions: the finding, the answer now and in seven days, the working, what it runs on (DataSnack's models, published figures with their sources, and the reader's assumptions) and the record. With set, the service recomputes with those assumptions; the result is marked custom.

Input parameters:

- `set` (object): Optional: the reader's assumptions to change, by key (such as {"tank": 18}); at most eight
- `slug` (string, required): The question's slug, from the questions tool or its page address

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `world_scenario` (~89 tokens)

The World Machine's what-if

Set one World Machine model's number in seven days and read the models that move through the links. These are the models' numbers under that assumption, not predictions that it will happen.

Input parameters:

- `series` (string, required): A model's series key (such as yahoo:CL=F) or its model id
- `value` (number, required): Its number in seven days, in the model's unit

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `overnight` (~42 tokens)

DataSnack overnight

What DataSnack's agents did last night: rounds run, model changes kept and rejected, the biggest miss, where DataSnack and the market differ most, and the scoreboard.

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `scoreboard` (~46 tokens)

DataSnack scoreboard

How DataSnack's models and agents did over the last 30 days: how far off the seven-day forecasts landed, how often they beat standing still, and how often the direction was right.

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `calibration` (~33 tokens)

Prediction-market calibration

How often prediction markets came true at each price, by days before they closed, from the markets DataSnack follows that have resolved.

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `get_reference_workbook` (~65 tokens)

Free DataSnack Excel model

A free DataSnack Excel workbook with working formulas: the tariffs → mortgage rates lab, a chain of five models fitted on public FRED data (import prices, producer prices, consumer prices, the 10-year yield and the 30-year mortgage rate). No account needed.

Output parameters:

- `as_of` (string): When the data was last worked on (RFC 3339), if known
- `url` (string): The canonical datasnack.ai page for this answer

### `get_me` (~27 tokens)

Your DataSnack account

The signed-in reader's DataSnack account: handle, plan, and coverage used this month.

### `list_library` (~21 tokens)

Your followed models and coverage

The models the signed-in reader follows and the markets they cover.

### `follow_model` (~62 tokens)

Follow a model

Follow a model (or market) so its changes show in the reader's DataSnack Library and notices.

Input parameters:

- `id` (string, required): A DataSnack model id (ch:…), a datasnack.ai/m/… URL, or a market id from search_models

### `unfollow_model` (~50 tokens)

Stop following a model

Stop following a model (or market).

Input parameters:

- `id` (string, required): A DataSnack model id (ch:…), a datasnack.ai/m/… URL, or a market id from search_models

### `list_notices` (~31 tokens)

Your recent notices

The signed-in reader's DataSnack notices from the last 48 hours: changes to followed and covered models.

### `cover_status` (~79 tokens)

Coverage of a market

Whether the signed-in reader can cover a market now (so DataSnack builds or keeps working its model every night) and, if not, why; with the reader's allowance and credits.

Input parameters:

- `id` (string, required): A DataSnack model id (ch:…), a datasnack.ai/m/… URL, or a market id from search_models

### `cover_market` (~97 tokens)

Cover a market

Cover a market for the signed-in reader: DataSnack builds a model for it (or keeps working the one it has) every night, and the reader can export it to Excel. Uses one of the month's coverages from the reader's plan, or a coverage they bought.

Input parameters:

- `id` (string, required): A DataSnack model id (ch:…), a datasnack.ai/m/… URL, or a market id from search_models

### `export_options` (~60 tokens)

Can this model be exported?

Whether the signed-in reader can export a model to Excel now and, if not, why (they need to cover its market).

Input parameters:

- `id` (string, required): A DataSnack model id (ch:…) or a datasnack.ai/m/… URL

### `export_model` (~88 tokens)

Export a model to Excel

Create an Excel workbook of a DataSnack model the signed-in reader covers, with the model's equations as working formulas, its inputs and its record, and return a download link. Waits up to 20 seconds for the workbook; get_export finishes a slower one.

Input parameters:

- `id` (string, required): A DataSnack model id (ch:…) or a datasnack.ai/m/… URL

### `get_export` (~33 tokens)

Get an Excel export

The status of an Excel export and, when it is ready, its download link.

Input parameters:

- `export_id` (string, required)

### `list_exports` (~17 tokens)

Your Excel exports

The signed-in reader's recent Excel exports.

### `start_checkout` (~51 tokens)

DataSnack Plus or a coverage: checkout link

A Stripe checkout link for the signed-in reader to open in their browser and pay: DataSnack Plus monthly or yearly, or one market coverage. Nothing is charged by this tool.

Input parameters:

- `product` (string, required)

## Diagnostics

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

## Score history

- 2026-11-21: 38
- 2026-11-20: 36
- 2026-11-19: 33
- 2026-11-18: 33
- 2026-11-17: 23
- 2026-11-16: 23
- 2026-11-15: 23
- 2026-11-14: 71
- 2026-11-13: 71
- 2026-11-12: 70
- 2026-11-11: 70
- 2026-11-10: 69

## Common questions

### What is the DataSnack MCP server?

DataSnack is an MCP server listed in the public MCP registry as ai.datasnack/datasnack. Seven-day forecasts of real-world numbers, linked and graded daily; sign-in adds Excel exports. This page covers its hosted endpoint (https://datasnack.ai/mcp).

### Is the DataSnack MCP server safe to use?

DataSnack scores 38 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the DataSnack MCP server expose?

DataSnack exposes 23 tools: search_models, get_model, world, head_to_head, questions, and 18 more. Their descriptions and schemas cost roughly 1,411 tokens of context every time the server is loaded.

### Does the DataSnack MCP server require authentication?

Yes. DataSnack asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the DataSnack MCP server still maintained?

DataSnack is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the DataSnack MCP server?

VerifyMCP ran 5 checks on DataSnack, covering TLS certificate, Authorization, HTTPS, HSTS header and 1 more. 6 items could not be completed, a gap on our side rather than a finding about DataSnack: Transport, Schema quality, Stability, Tool coverage and 2 more. 6 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://datasnack.ai/mcp
- Website: https://datasnack.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-datasnack-datasnack/datasnack.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-datasnack-datasnack/datasnack/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-datasnack-datasnack/datasnack.json
- HTML version of this page: https://verifymcp.io/servers/ai-datasnack-datasnack/datasnack
