MissedTakes
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Graded track records of NFL and election pundits: records, leaderboards, takes, game and race calls.
| Author | co.missedtakes |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 1947 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"MissedTakes": {
"url": "https://missedtakes.co/api/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (9)
find_entitiesread-onlyLook up the slug MissedTakes uses for a pundit, a publication (outlet), an NFL team, an NFL player or a prediction type, by full or partial name. Call this first whenever the user names someone: the other tools take slugs, never names. Only pundits and outlets with a public page are returned.
Parameters:
query(required) — string — A name or part of one, e.g. "Kiper".kind— string — Restrict to one kind. Omit to search all five.
Hints: read-only yes · destructive no · idempotent yes · open-world no
leaderboardread-onlyThe ranked NFL pundit leaderboard, the same rows missedtakes.co/nfl/leaderboard prints: MissedTakes Score (skill against a naive baseline, which is the ranking), accuracy, graded takes and articles. Provisional records (under ten graded articles) are not ranked. Pass a prediction type slug (find_entities, kind prediction_type) to rank within one kind of claim, such as mock drafts.
Parameters:
limit— integer — How many rows, 1-25 (default 10).typeSlug— string — A prediction type slug to rank within. Omit for the overall NFL board.
Hints: read-only yes · destructive no · idempotent yes · open-world no
pundit_recordread-onlyOne pundit's published NFL record: overall MissedTakes Score, accuracy and sample size, the record broken down by prediction type, and any Pundit of the Week or Month awards. For their election record, call election_pundit.
Parameters:
punditSlug(required) — string — The pundit's slug, from find_entities.
Hints: read-only yes · destructive no · idempotent yes · open-world no
outlet_recordread-onlyOne publication's NFL record, aggregated across everyone writing or speaking under its banner: overall and by prediction type, with how many pundits contribute.
Parameters:
outletSlug(required) — string — The outlet's slug, from find_entities.
Hints: read-only yes · destructive no · idempotent yes · open-world no
list_takesread-onlyIndividual NFL predictions: who made them, when (claimedAt is the publication date), a short excerpt of the wording, the grade (accuracy 0-100, or pending) and the grading arithmetic. Filter by pundit, outlet, prediction type, team, player, season, verdict (hit is 80+, close is 40-79, miss is under 40) and claim dates. 25 rows a page; pass page for more.
Parameters:
page— integer — 1-based page of 25 rows.sort— stringverdict— string — hit is 80+, close 40-79, miss under 40; graded is any grade.teamSlug— string — Only takes about this team.typeSlug— string — Only this prediction type.outletSlug— string — Only takes published by this outlet.playerSlug— string — Only takes about this player.punditSlug— string — Only takes by this pundit.seasonYear— integer — Only takes tied to this NFL season.claimedAfter— string — Only takes published on or after this date (YYYY-MM-DD).claimedBefore— string — Only takes published on or before this date (YYYY-MM-DD).
Hints: read-only yes · destructive no · idempotent yes · open-world no
game_roomread-onlyWhat the pundits predicted for one NFL game, counted the way its page on missedtakes.co counts it: how many took each side (one voice per pundit, their latest call standing), the median predicted margin, each pundit's latest score call as a home-minus-away margin, and the final score once the game is played. Identify the game by season year, week (1-18 regular season, 19-22 playoffs) and either team's slug.
Parameters:
seasonYear(required) — integer — The NFL season, e.g. 2026.week(required) — integer — Week 1-18 for the regular season, 19-22 for the playoffs.teamSlug(required) — string — Either team's slug, e.g. "lions" (find_entities, kind team).
Hints: read-only yes · destructive no · idempotent yes · open-world no
election_racesread-onlyThe races, chamber control and the national House popular vote that pundits have called in an election cycle (the current one unless you pass cycle), most-called first: how many pundits called each, how the field splits (each pundit's latest pick counted once, and split into forecasters and commentators), calls in the last 7 days, and the VoteHub polling average where one exists. Filter by office (president, senate, house, governor, chamber, national) or two-letter state. Use it to find a race slug.
Parameters:
cycle— integer — The election cycle year. Omit for the current cycle.limit— integer — How many, 1-40 (default 15).state— string — Two-letter state code, e.g. "GA".office— string
Hints: read-only yes · destructive no · idempotent yes · open-world no
election_race_callsread-onlyThe individual calls on one race or chamber, newest first: who said it, when, what they picked or the number they named, a short excerpt of their wording, and the pundit's graded election record from past cycles. raceSlug comes from election_races, or is chamber:senate, chamber:house or national:house-vote.
Parameters:
raceSlug(required) — string — A race slug from election_races, or chamber:senate, chamber:house or national:house-vote.page— integer — 1-based page of 25 calls.cycle— integer — The cycle, for a chamber or the national vote. Omit for the current cycle.
Hints: read-only yes · destructive no · idempotent yes · open-world no
election_punditread-onlyOne pundit's election record: their graded record from past cycles (accuracy, MissedTakes Score, sample size) and their calls in the current cycle, newest first. Look up by slug, or by part of their name.
Parameters:
name— string — Part of the pundit's name, when the slug is unknown.cycle— integer — The cycle whose calls to list. Omit for the current one.punditSlug— string — The pundit's slug.
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.