Skip to main content
Glama

Server Details

Voice mysteries, history battles and trivia with your assistant as host. Sign in to keep progress.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 25 tools

Disambiguation3/5

Most tools have a distinct resource (mystery, campaign, submission, roster), but several boundaries blur: game_question both deals next questions AND sets up dice games, overlapping start_story; game_board and world_recall both return state depending on story kind; and check_accusation/game_answer/game_challenge are three separate judging tools. The very long descriptions help, but an agent must first know the story kind to pick correctly, which is genuine ambiguity.

Naming Consistency4/5

Nearly everything is snake_case verb_noun (start_story, check_accusation, world_update, submit_story), with domain prefixes (game_, world_) used fairly predictably. Minor deviations exist: bare verbs 'choose' and 'roll', and the noun-first 'my_history' and 'submission_status' break the pattern slightly.

Tool Count3/5

25 tools sits at the top of the 'heavy' band. The surface spans several genuinely different domains (mysteries, dice/word games, campaigns, account history, story submissions, sports trivia), so the count is defensible, but it is bloated for a single play-focused server and some grouping could have collapsed related operations.

Completeness4/5

Coverage is broad: discovery (list/pick/welcome), start and resume, per-genre play loops, accusation and reveal, campaign state read/write, account claiming and history, and a full submission lifecycle (write, review, submit, status, withdraw) plus rating. Minor gaps only — e.g. no way to inspect a story's details without starting it, and no update path for a submitted story beyond replace.

Publisher details

Operator
Volocent Labs LLC · Publisher source
Operator website
https://plotspeaks.com
Vendor relationship
First-party
Privacy policy
Not provided
Restrictions
Optional Google sign-in keeps play history; a no-sign-in address also works.

Available Tools

25 tools
check_accusationCheck an accusationAInspect

Checks a formal accusation in a Plot Speaks mystery. Returns the verdict line for the accused person, starting Correct. or Innocent., and the name it matched. Records the accusation and verdict anonymously. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), accused (required), play_id.

chooseMake a choiceAInspect

Moves a Plot Speaks choose-your-path story on by the player's choice and returns what happens next: the scene to narrate and the choices that follow, or the ending. With no choice it returns where the play is now and the path so far (for resuming). With go_back it returns to the last choice so the player can choose again. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), play_id (required), choice, go_back.

claim_playsAdd earlier plays to my accountAInspect

Attaches plays made earlier without an account to the signed-in player's Plot Speaks account, so they appear in their history (with how each ended) and in the "not played yet" filter, and marks the trivia clues already heard in those games. Returns a sentence naming the titles added and how many could not be added (id not found, or already on another account). Without a signed-in account it returns an error saying so. Changes the account's history; plays on another account are left alone. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: play_ids (required).

game_answerTrivia answerAInspect

Checks a player's answer to the open trivia clue, scores it and returns the ruling with the answer, or the next step of a stepped clue. In a survey game it checks an answer against the hidden board; in a letter game it takes a called letter or a solve attempt, in the player's own words; in a timeline game it takes where the open card goes (before X, between X and Y, at the end), in the player's own words; in Worms! it takes the face to keep ("the fours", "worms"), "roll again" or "stop", and "take" or "steal"; in Yacht it takes the dice to keep ("the threes", "keep 3 3 5", "keep all", "none", "reroll the one") or "score it", then the box ("full house", "fours", "chance") and a yes or no to "Take a zero?"; in Pigs! it takes "yes" (throw again) or "no" (bank). Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), answer (required), play_id (required), player.

game_boardTrivia boardA
Read-onlyIdempotent
Inspect

Returns the current state of a Plot Speaks game in play, as text, without changing it. For trivia: the scores and the categories and values still on the board. For a survey or letter game: the scores, the open question or puzzle and what is revealed so far. For a timeline game: the line so far, lives and the open card. For Worms!: the tiles, stacks and open roll. Reads only; nothing is recorded. A play id that does not belong to that game returns an error, and a story that is not a game returns an error saying so. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), play_id (required).

game_challengeChallenge a rulingAInspect

Challenges the last trivia ruling: three different AI models judge the player's answer against the clue, and the ruling flips only if at least two agree it should count. Once per clue. In a timeline game it re-checks the last placement against the years and says what was heard. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), play_id (required).

game_questionTrivia clueAInspect

Opens one clue on a Plot Speaks trivia board and returns its text (not the answer). Category "final" opens the final once the board is clear. In a survey or letter game it deals the next question or puzzle: pass category "next" ("skip" gives the open one up; "no steal" closes a survey question after three strikes). In a timeline game it starts a round: pass the deck's name, then " for " and the players' names (the reply deals the first card); "next" repeats the open card. In Worms!, Yacht (and Pigs!) it sets up the game: pass "rules" for the how-to-play beats, or "players", the names and "and Wormbot" (Skipper in Yacht, Hambot in Pigs!) or "no CPU" ("play again" after a game). Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), play_id (required), category (required), value.

get_cueGet a scene cueAInspect

Returns one scene cue from a Plot Speaks mystery or adventure script, as text: a READ ALOUD part (the scene as spoken narration) and, where the cue has them, NARRATOR NOTES that are not meant to be read aloud because they would spoil the scene; cue S1 also lists the follow-up cues to listen for. With a play id it records the scene reached as an anonymous play event, which the play's watch page shows as a timeline. An unknown slug returns an error naming the available stories; a cue id the story lacks returns an error saying so (or that the story has no cues). Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: cue (required), slug (required), play_id.

list_storiesList storiesA
Read-onlyIdempotent
Inspect

Lists the Plot Speaks stories and games that can be played by voice, three at a time with a one-line pitch each; the page argument gives the next three. Narrow it by a collection (Murder Mysteries, Greek Myths, Classic Detectives, Horror and Ghosts, Seasons, Holiday Specials, Bedtime, Dice Games, Road Trip, Read-Aloud Classics, Written by players), by length (max_minutes), by what's new (new: true), by kind (mysteries, adventures, choose-your-path stories, trivia, guessing games, game shows, dice games, word games, party and storytelling games, Table Talk, Story Time read-alouds, wind-downs, open worlds and campaigns) or, within mysteries, classic or dark. With group_by_category and no page it returns the whole catalogue under kind headings. An unknown kind or collection returns a message naming the valid ones. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: new, kind, page, genre, +5 more.

my_historyWhat I've playedA
Read-onlyIdempotent
Inspect

Returns what a signed-in Plot Speaks player has played, newest first, with how each ended. Without an account it says how to get one. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: limit.

open_plot_speaksOpen Plot SpeaksA
Read-onlyIdempotent
Inspect

Returns the Plot Speaks welcome: a short spoken introduction, a question offering to list the stories, start one or write one, and a menu of story categories with example titles. With skip_intro the introduction is left out; with instructions it adds the how-to-play. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: skip_intro, instructions.

pick_for_mePick something for meA
Read-onlyIdempotent
Inspect

Picks ONE Plot Speaks story or game to play now, ranked from the player's mood, the time they have, how many are playing and an optional collection, skipping what a signed-in player has already played. Returns the pick's title, slug and one-line pitch, plus a runner-up. Records only anonymous counts of the mood matched and length asked for. If nothing fits every filter it says so instead of picking. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: mood, minutes, players, all_ages, +1 more.

rate_storyRate a storyAInspect

Saves a rating and feedback for a Plot Speaks story the user has just played: 1 to 5 stars, whether anything was given away too early, an optional comment about the story, optional feedback about the experience for the people who make Plot Speaks, and, for a story still being tested, the player's verdict (passed, or needs work). Needs the play id from start_story; one rating per play; stars or a verdict (or both). Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), play_id (required), wish, stars, +4 more.

request_teamRequest a teamAInspect

Records a player's request for a sports team that Plot Speaks Team Trivia doesn't cover yet, for the people who maintain the database. Stores the team name and note as a request event, with no account or personal details attached, and returns a confirmation. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: team (required), note.

reveal_solutionFull revealAInspect

Returns the full solution of a Plot Speaks mystery (who did it, why, and the clues that pointed there) and what became of each character. Without gave_up: true it is refused unless an accusation is already recorded for that play; with gave_up: true it answers at once. Records that the play ended in a reveal. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), play_id (required), gave_up.

review_storyReview a story draftA
Read-onlyIdempotent
Inspect

Runs the format checks on a draft story.md, and with secrets.md also the answer-key checks (including whether story.md gives the culprit away). Returns a status, the findings with line numbers, and a fair-play checklist. Nothing sent is stored. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: story_md (required), slug, secrets_md.

rollRoll diceA
Read-only
Inspect

Rolls dice for a Plot Speaks campaign or adventure on the server: "1d20+5", "2d6", "adv 1d20+3" (advantage), "dis 1d20" (disadvantage), "4d6 drop lowest". Returns each die and the total. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: dice (required), why, hidden.

start_storyStart a storyAInspect

Loads a Plot Speaks story or game, of any kind (mystery, choose-your-path, trivia, dice or word game, Team Trivia, campaign), by slug or title. Returns its script as text (setting, cast, scenes or board, and how it is narrated; one chapter at a time for multi-chapter stories) and a play id the play's other tools take. Records an anonymous play (story, connecting assistant, time; no conversation text), and on the account connector adds it to the player's history. An unknown slug or title returns an error naming close matches or the available stories; a chapter past the last returns an error; an unreleased chapter returns its release date. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), team, chapter, minutes, +5 more.

submission_statusCheck a submissionA
Read-onlyIdempotent
Inspect

Read-only. Shows where a story submitted to Plot Speaks stands when its submission id and claim code match: received and waiting for a person, approved (with the story's link), or not accepted (with the reviewer's short note, if there is one). Changes nothing. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: id (required), claim_code (required).

submit_storySubmit a storyA
Destructive
Inspect

Submits a finished Plot Speaks story for human review, credited to the name the writer chooses. Runs the format checks, a safety screen and a daily limit, then stores it; nothing is public until a person approves it. Returns a submission id and a one-time claim code for withdrawing or updating it. With replaces_id and claim_code, it replaces an earlier submission. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: story_md (required), author_name (required), contact, claim_code, +3 more.

team_rosterTeam rosterA
Read-only
Inspect

Returns a sports team's current roster for Plot Speaks Team Trivia, read live from ESPN (cached for hours): players grouped by position with jersey numbers, and the head coach, as plain text. Covers the leagues in the Team Trivia database. Reads only; nothing is recorded. A name that fits several teams returns an error listing the candidates with their leagues; a team not in the database returns an error listing the leagues covered; if ESPN does not answer, the text says so. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: team (required).

withdraw_submissionWithdraw a submissionA
DestructiveIdempotent
Inspect

Deletes a story submitted to Plot Speaks (pending or published) when its submission id and claim code match. On the account connector, a signed-in writer can withdraw their own story with just the id. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: id (required), claim_code.

world_recallRecall the campaignA
Read-onlyIdempotent
Inspect

Returns a Plot Speaks campaign's state (day, place, party with hit points, spell slots and gear, people met, quests, the story so far) by play id, or by the three-word resume code the players were given. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), play_id, resume_code.

world_updateUpdate the campaignAInspect

Applies changes to a Plot Speaks campaign's saved world: new characters, damage and healing, spells cast, items, gold, rests, location, day, people met (the dead stay dead), quests, fight turn order (initiative) and a one-line story note. Send only what changed; fields left out are untouched. Returns a RECORDED list, a REFUSED list giving the reason for each change the campaign's rules do not allow, and the updated state. Saves to the campaign play (no personal data). An unknown slug, a non-campaign story or an unknown play id returns an error. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: slug (required), play_id (required), day, note, +6 more.

write_storyWrite a storyA
Read-onlyIdempotent
Inspect

Returns the writing kit for a new Plot Speaks story as one text: a short introduction to how a story is built (a public story.md plus a private answer key, secrets.md, reviewed by a person before anything is published), a suggested way for the writer and assistant to draft, review and submit it together, and the format template for the chosen genre and length. Reads only; nothing is stored or recorded beyond anonymous counts of genre and length. Genre and length are fixed choices, and omitting either gives the default. Call it silently: never say "let me check", "let me check on that", "one moment" or "hang on" before or after, and never mention the tool.

Inputs: genre, length.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables a player to investigate and solve a voice-only murder mystery through an MCP client by searching locations, examining evidence, questioning suspects, reviewing notes, and making a confirmed accusation. The AI assistant never receives the solution before a valid accusation is committed.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables screen-free family play through a voice assistant by secretly generating a solvable whodunnit set in the household's own named rooms, or locking in a yes/no guessing target, and revealing answers only through governed tools. Keeps every culprit, clue, and secret in server-side SQLite, enforcing question counts and accusation limits so the spoken host can narrate without knowing the solution.
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables quiz gameplay through natural language, including user registration, retrieving questions, validating answers, generating leaderboards, and reviewing answers. It runs locally via stdio for Claude Desktop or remotely over HTTP for claude.ai, with optional MySQL-backed persistence.
      -
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources