Seven-day forecasts of prediction-market questions (Kalshi and Polymarket), each an explicit equation graded daily against standing still, with every miss on the record. Search and read models with their record, see last night's work, the scoreboard and market calibration, and get a free Excel model with no account; sign in with OAuth to follow models, cover markets and export covered models as Excel workbooks with working formulas.
Scored across 21 tools
Most tools target a clearly distinct resource or action: search_models vs get_model, follow_model/unfollow_model, and the export trio (export_model, get_export, list_exports) are well separated. The soft spots are cover_status vs export_options (both are 'can I do X now and if not, why' entitlement checks) and the four read-only stats tools (calibration, scoreboard, overnight, head_to_head), which require reading descriptions carefully to distinguish.
Action tools follow a solid verb_noun pattern (cover_market, export_model, follow_model, list_exports, search_models, start_checkout). The deviation is the report/dashboard tools, which are bare nouns (calibration, scoreboard, overnight, head_to_head, world), so the convention is not universal, though it is readable and arguably intentional.
At 21 tools this sits in the heavy band for a single product surface. Several are defensible (search/read/follow/cover/export/checkout), but pairs like cover_status + export_options and the four separate stats endpoints could be consolidated without losing capability.
The main lifecycle (search → read → follow → cover → export → pay) is covered, including export polling and free reference material. Gaps remain: no way to stop covering a market or release a coverage, no plan/billing management beyond start_checkout, and no tool to read a single World Machine model or list its models individually.
How often prediction markets came true at each price, by days before they closed, from the markets DataSnack follows that have resolved.
Inputs: no named parameters. Returns: url, as_of
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.
Inputs: id (required).
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.
Inputs: id (required).
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.
Inputs: id (required).
Whether the signed-in reader can export a model to Excel now and, if not, why (they need to cover its market).
Inputs: id (required).
Follow a model (or market) so its changes show in the reader's DataSnack Library and notices.
Inputs: id (required).
The status of an Excel export and, when it is ready, its download link.
Inputs: export_id (required).
The signed-in reader's DataSnack account: handle, plan, and coverage used this month.
Inputs: no named parameters.
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.
Inputs: id (required). Returns: url, as_of
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.
Inputs: no named parameters. Returns: url, as_of
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.
Inputs: target. Returns: url, as_of
The signed-in reader's recent Excel exports.
Inputs: no named parameters.
The models the signed-in reader follows and the markets they cover.
Inputs: no named parameters.
The signed-in reader's DataSnack notices from the last 48 hours: changes to followed and covered models.
Inputs: no named parameters.
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.
Inputs: no named parameters. Returns: url, as_of
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.
Inputs: no named parameters. Returns: url, as_of
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.
Inputs: query (required), limit. Returns: url, as_of
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.
Inputs: product (required).
Stop following a model (or market).
Inputs: id (required).
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.
Inputs: domain. Returns: url, as_of
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.
Inputs: value (required), series (required). Returns: url, as_of
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.