# The Tennis Desk (remote · thetennisdesk.com) Ratings, line win chances and lineup help for USTA NorCal adult league tennis, from public results. - Trust score: 75/100 (medium) - Change this week: +4 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-11-05 ## Components - remote · `thetennisdesk.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/chungty-thetennisdesk/api-mcp.md), [page](https://verifymcp.io/servers/chungty-thetennisdesk/api-mcp) ## Channel facts - Endpoint: `https://thetennisdesk.com/api/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `0.3.0` ## 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 2026-11-05. - **Endpoint Security**: 80/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. - 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. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 63/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 7654 tokens (~263/item across 29 items; 29 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 23/100 - Stability observed for 7 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. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 29 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 30 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the The Tennis Desk MCP server? The Tennis Desk is a hosted endpoint at https://thetennisdesk.com/api/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 chungty-thetennisdesk 'https://thetennisdesk.com/api/mcp' ``` ### Cursor ```json { "mcpServers": { "chungty-thetennisdesk": { "url": "https://thetennisdesk.com/api/mcp" } } } ``` ### VS Code ```json { "servers": { "chungty-thetennisdesk": { "type": "http", "url": "https://thetennisdesk.com/api/mcp" } } } ``` ### Codex ```toml [mcp_servers.chungty-thetennisdesk] url = "https://thetennisdesk.com/api/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "chungty-thetennisdesk": { "type": "remote", "url": "https://thetennisdesk.com/api/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add chungty-thetennisdesk --url 'https://thetennisdesk.com/api/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: chungty-thetennisdesk: url: "https://thetennisdesk.com/api/mcp" ``` ### Netclaw ```json { "McpServers": { "chungty-thetennisdesk": { "Transport": "http", "Url": "https://thetennisdesk.com/api/mcp" } } } ``` ### Vellum ```bash assistant mcp add chungty-thetennisdesk -t streamable-http -u 'https://thetennisdesk.com/api/mcp' ``` ### Other ```json { "mcpServers": { "chungty-thetennisdesk": { "type": "http", "url": "https://thetennisdesk.com/api/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. ### 2026-11-05 (score 75, +1) No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-11-03 (score 74, +1) - [security] Tool “query_club” rewrote its description, which is the text the model reads - [security] Tool “query_league_standings” rewrote its description, which is the text the model reads - [cosmetic] “query_club” reworded the description of “briefing” - [cosmetic] Tool “query_league_standings” changed its title: An unofficial league table → A league table ### 2026-11-01 (score 73, +1) No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-31 (score 72, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [functional] Server version: 0.2.0 → 0.3.0 ### 2026-10-30 (score 72, +1) - [functional improvement] Stability: unverified → 0.03 ### 2026-10-29 (score 71) First indexed and scored. ## MCP tools (29) ### `plan_lineup` (~377 tokens) Your lineup and line chances Plans a doubles and singles lineup for a team the Desk covers. It lists who has played most for your team this season, with their appearances, usual line and Desk level, the Desk's estimate of how they play now. Against a covered opponent it adds each line's win chance, each team's Desk level there and the expected number of lines won. Call it for 'what lineup should we play against X', 'who has played most for us' or 'how do we beat X'. Pass `unavailable` for your players who are out, but pass `lineup` only for the players the person put on each line. Needs a Desk Pass after the member's free forecast each week. Past that, a call gets the free part, with no chance for anything still to be played, and `deskPass`, whose `message` you give the person. Its error is free_forecast_used, or desk_pass_required for a key with no member. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `lineup` (array): Your own team's lineup, only as the person states it, line by line. Never fill it in yourself. Each line named is read from those players. - `opponent` (string): The opponent team to plan against, by name or Desk page link. Optional. - `season` (integer): Season year. Defaults to the current season. - `team` (string, required): Your team, e.g. 'Belvedere 18AM3.5A', or its Desk page link or number. Must be a covered team. - `unavailable` (array): Players on YOUR team who are out. They leave your list and the averages your side of each line is read from. Names may be abbreviated ('Jane'). ### `query_team_record` (~334 tokens) A team's results and next matches Returns the recorded lines of any team the Desk covers, in any league and season, each with an evidenceId you can cite. It also gives the team's record, which is already counted, every team match of the period and its next matches. Call it when someone asks about a named team's matches, results or next match, or before you state a fact about them. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `date` (string): Optional match day, as YYYY-MM-DD, e.g. '2026-02-05'. The rows are then that day's lines, from any season unless `season` is given. Pass it when the question names the day of a match. - `includeAllSeasons` (boolean): Set true ONLY when the user explicitly asks about prior years / all history. - `limit` (integer): Max rows to return (default 9, max 60). - `phase` (string): Optional competition phase: 'sectionals', 'playoffs', 'postseason', or 'regular season'. Pass it when the member names one — a sectional match keeps its REGULAR-SEASON league name in our data, so the… - `season` (integer): Optional season year to filter to, e.g. 2026 - `team` (string, required): Team name or partial name to resolve, e.g. 'Tiburon' or 'Mill Valley men's 18'. Or the team's Desk page link or number. ### `query_matchup` (~194 tokens) Recent results between two teams Returns the recorded lines from the scorecards where two named teams played each other, in any season, each with an evidenceId. Call it for the head-to-head between two teams, or before you state a fact about it. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `includeAllSeasons` (boolean): Set true ONLY when the user explicitly asks about prior years / all history. - `limit` (integer): Max rows to return (default 9, max 60). - `season` (integer): Optional season year to filter to, e.g. 2026 - `team_a` (string, required): First team name or partial name to resolve. Or the team's Desk page link or number. - `team_b` (string, required): Second team name or partial name to resolve. Or the team's Desk page link or number. ### `query_roster` (~230 tokens) A team's roster and ratings Returns a team's roster for a season, one row per player with an evidenceId: name, NTRP rating, wins, losses, matches and Desk level. Call it when someone asks who is on a team, or before you state a fact about a roster. Pass `season` when the person named a year, because without it the answer covers the current season. If `moreRows` is true, call again with a larger `limit`, up to 60. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `includeAllSeasons` (boolean): Set true ONLY when the user explicitly asks about prior years / all history. - `limit` (integer): Max roster rows to return (default 30 = the full roster, max 60). Omit to get the whole team. - `season` (integer): Optional season year to filter to, e.g. 2026 - `team` (string, required): Team name or partial name to resolve. Or the team's Desk page link or number. ### `query_player_history` (~190 tokens) A player's recent results Returns the recorded lines a named player appeared in, as cited rows told from the player's side, with the player's record, which is already counted by season, team and stage. Call it when someone asks about a player's results, form or history. Never guess at their injury or availability, because the Desk does not hold it. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `includeAllSeasons` (boolean): Set true ONLY when the user explicitly asks about prior years / all history. - `limit` (integer): Max rows to return (default 9, max 60). - `player` (string, required): Player name to resolve, e.g. 'First Last'. Or the player's Desk page link or number. - `season` (integer): Optional season year to filter to, e.g. 2026 ### `query_match_log` (~166 tokens) Desk level, match by match Returns a player's match-by-match rating history for one season: each match they played, their level before and after it, and the other players on court with their levels then. Call it when someone asks how a player's level changed, how they reached it, what one result did to it, or asks to see their matches. Prefer it to query_player_history when the question is about the level rather than the results, because it follows the level match by match. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `player` (string, required): Player name as the member wrote it. Or the player's Desk page link or number. - `season` (integer): Season year. Omit for the current season. ### `compute_aggregate` (~332 tokens) A team's win rate and counts Works out one number for any covered team, in any league or season, in code from its recorded lines: `win_rate`, `win_count`, `loss_count` or `match_count`. Call it whenever you would state a count, an average or a win rate, and quote its value exactly rather than working one out. With no `phase` it counts the playoffs and sectionals too, so pass phase:'regular season' for a league record alone. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `includeAllSeasons` (boolean): Set true ONLY when the user explicitly asks about prior years / all history. - `kind` (string, required): Which number to compute, over the lines the team played: 'win_rate' (the share of them won, from 0 to 1), 'win_count' (lines won), 'loss_count' (lines lost) or 'match_count' (lines played). - `phase` (string): Optional competition phase: 'sectionals', 'playoffs', 'postseason', or 'regular season'. Pass it when the member names one, or when they ask for a LEAGUE record — a sectional match keeps its REGULAR-… - `season` (integer): Optional season year to filter to, e.g. 2026 - `team` (string, required): Team key or display name. Or the team's Desk page link or number. ### `compute_roster_strength` (~242 tokens) Each rating group's record Splits a team's roster by published NTRP level and gives each level group's players, wins, losses and win rate this season, over every league line those players appeared in. Call it for a roster's shape rather than its results, as in 'how strong is their 4.0 half' or 'who carries this team'. It works even before a season has been played, because it then reads the season before. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `phase` (string): Optional competition phase: 'sectionals', 'playoffs', 'postseason', or 'regular season'. Pass it when the member names one, or when they ask how a level group did in their LEAGUE — a sectional match… - `season` (integer): Optional season year, e.g. 2026 - `team` (string, required): Team key or display name. Or the team's Desk page link or number. ### `compute_match_line_ratings` (~174 tokens) Matches ranked by lineup strength Ranks a team's recorded matches by how strong a lineup it fielded, from each player's current Desk level, so it is not a rating at the time of the match. Call it when someone asks which match had the strongest or weakest lineup, or how a team's line strength moved. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `includeAllSeasons` (boolean): Set true ONLY when the user explicitly asks about prior years / all history. - `season` (integer): Optional season year to filter to, e.g. 2026 - `team` (string, required): Team key or display name to resolve, e.g. 'Belvedere mixed 8.0'. Or the team's Desk page link or number. ### `query_player_rating` (~149 tokens) A player's Desk level and record Returns the Desk's read of a named player: their Desk level, their record by season, team, stage and format, the model card id and the lines behind it. Call it when someone asks how strong a player is, or about their rating, level, trend or bump risk. The USTA band is not here, because it is the `rating` on a query_roster row. The Desk publishes no bump prediction. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `player` (string, required): Player name to resolve, e.g. 'First Last'. Or the player's Desk page link or number. ### `predict_matchup` (~269 tokens) One line's win chance Gives the home side's win probability for one line between named players. It weighs each player's Desk level, how a pair plays together and who is available, while a player the Desk has not yet rated gets a default level. Call it when someone asks who would win, the odds of a matchup, or how a pairing stacks up. Needs a Desk Pass after the member's free forecast each week. Past that, a call gets the free part, with no chance for anything still to be played, and `deskPass`, whose `message` you give the person. Its error is free_forecast_used, or desk_pass_required for a key with no member. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `away_players` (array, required): Away-side player name(s), ideally as they appear on recorded lines. Each may also be a player's Desk page link or number. - `home_players` (array, required): Home-side player name(s), ideally as they appear on recorded lines, e.g. 'Last, First'. Each may also be a player's Desk page link or number. - `line_type` (string): Optional; inferred from side sizes when omitted. One of 'singles' or 'doubles'. ### `query_team_forecast` (~223 tokens) Upcoming matches Returns a team's upcoming matches on the league schedule, or those of every team a player is on: the opponent, the day, the start time, and home or away. Call it for a next match, today's or tomorrow's match, or the schedule. Pass `team` for a named team, or `player` for a first-person ask like 'who am I playing'. It gives no team win chance. A team match's chance is only in the live playoff report from project_standings, which comes with the Desk Pass. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `player` (string): Player whose teams' upcoming matches to fetch, e.g. 'First Last'. Or the player's Desk page link or number. - `team` (string): Team name to resolve, e.g. 'Belvedere mixed 8.0' or 'BELVEDERE TC 40MX8.0A'. Or the team's Desk page link or number. ### `query_club_teams` (~202 tokens) A club's teams this year Returns the teams a named club fields this year, and which of them plays next. Call it whenever someone asks about a whole club by name, before you narrow the question to a single team. For how the club is doing, call query_club, which reads the club's page. Pass any league words the person used in `qualifier`, such as 'combo', 'mixed', 'womens', '40 & over' or '3.5', because dropping them answers a different question. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `club` (string, required): The club name, e.g. 'Belvedere'. - `qualifier` (string): Any league words the asker used alongside the club — 'combo', 'mixed', 'womens', '40 and over', '3.5'. Omit only when they named the club alone. ### `query_club` (~476 tokens) What a club's page shows Returns what a club's page on The Tennis Desk shows, in one call. That is its teams in a season by league, each with its place in the Desk's league table and its record. It also gives the club's next matches, latest results and record against each other club. Call it when someone asks how a club is doing, its record against other clubs, or where its teams stand. For only its list of teams, or which plays next, query_club_teams is enough. Pass `club`: the club's name as people say it or as USTA prints it, or its page address or number. Pass `season`, a year, for that season's page, and `briefing` true for the club's week. A team's `firstPlace` says whether it can still finish first, which assumes each scheduled match is played. In a result, * marks a line won or lost by default. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `briefing` (boolean): True for the club's week instead of its page: every team match in the next 7 days, counting the day of the call in Pacific time, each with the other team's place in the Desk's league table and their… - `club` (string, required): The club: its name as people say it or as USTA prints it, e.g. 'Scott Valley', or its club page address or number, e.g. '/c/218'. - `season` (integer): A season year, 2022 or later: the club's page in that season, its teams, places and records then. Leave it out for the newest season the club fielded a team. A season the club has no team in is not f… ### `query_my_teams` (~173 tokens) Your own teams Returns the member's own teams, the ones they are on or have played for, which come from their affiliations. Call it when the person asks about their own teams, as in 'what teams am I on', and set thisYear:true for this year's. A question that names a team, a club or a player is about that one, so use the other tools for it, signed in or not. Needs a signed-in member, because it answers about them. A key with no member gets the error member_required. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `thisYear` (boolean): Set true for 'this year / this season' — the current league year's teams only. Omit for all covered teams. ### `query_cohort_standing` (~311 tokens) Where you rank by Desk level Ranks a group of players by Desk level and gives the member's place in it. Call it for 'where do I stand', 'how do I compare to the top players', a ranking or a percentile, or the top players in an age group or level. Define the group with `ageBand`, `division` and `level`, or leave them out so it fills the group from the member's team. Needs a signed-in member, because it answers about them. A key with no member gets the error member_required. Input parameters: - `ageBand` (string): Age group: '18', '40', '55', '65', or '70' (the '& Over' band). - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `division` (string): 'men', 'women', or 'mixed' — the gender ladder. Omit to use the member's own. - `includeAllSeasons` (boolean): Set true ONLY to pool cohort membership across all years. - `level` (string): NTRP level as a string, e.g. '4.0' or '8.0' (mixed). Omit for a whole age-group ladder. - `season` (integer): Optional league year for cohort membership, e.g. 2026. Defaults to the current season. - `topN` (integer): How many top players to show (default 10). ### `query_league_standings` (~354 tokens) A league table Builds the Desk's league table for a team's flight, with the named team's place, which it ranks from recorded results by the league's own rule and tie-breaks. Call it for the standings, how a team finished, who won the league or 'the table'. Pass the team name, or nothing for the member's own team. For a whole league, pass `league` and `area` instead, such as "55 & over men's 8.0" and 'Marin'. Never pass a club or an area as the team. Input parameters: - `area` (string): The area of that league, as the Desk names it, e.g. 'Marin' or 'San Francisco'. Used only with `league`. - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `league` (string): A league to build the table of when no team is named, with every league word the question gives, the age group included: its name, e.g. 'Adult 55 & Over Mens 8.0', or its words, e.g. "55 & over men's… - `season` (integer): League year, e.g. 2025. Defaults to the current season. - `team` (string): Team or club name whose league table to build, e.g. 'Belvedere' or 'Belvedere mixed 8.0'. Omit to use the signed-in member's own team, or to ask by `league`. Or the team's Desk page link or number. ### `plan_lineup_from_availability` (~367 tokens) A lineup from NorCal availability Plans a lineup from the availability a member's agent read on the USTA NorCal league site, so the agent can fill in the lineup form. Pass the team, the match and each player's answer in USTA's own words: yes, No, maybe, call last, First shift only or Second shift only. The result also holds the values for the lineup form, and what to confirm with the member before Save. Each line's win chance needs a Desk Pass after the member's free forecast each week. The Desk never acts on the USTA site, so the member, or their own agent in their own session, presses Save. Call it when someone pastes or describes who can play a match and asks for a lineup. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `availability` (array, required): Each player's answer, as the agent read it on NorCal's availability grid or as the member pasted it. - `date` (string): The match date, as 2026-10-24. With opponent, or alone. With neither, the plan is for the team's next match. - `matchId` (string): USTA NorCal's own id for the match, read from the link on the team page. Optional: it fills in the form's path. - `opponent` (string): The other team in the match, as the schedule names it. With date, or alone. - `season` (integer): Season year. Defaults to the current season. - `team` (string, required): The member's team: the Desk's team id, which is USTA NorCal's own team id, a link to its team page, or its name. ### `prepare_score_entry` (~392 tokens) Values for the score form Prepares the values for the score form on the USTA NorCal league site, from the scores a member reports. Pass the team, the match and each line: its players on both sides, its set scores, and its status when a line was not completed. Give the sets from the member's own side, unless scoresFrom says otherwise. Pass posted too, with each line as NorCal shows it, so it can list every line where the two differ. The Desk never acts on the USTA site, so the member, or their own agent in their own session, presses Submit. Call it when someone wants to enter or check a match score on NorCal. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `date` (string): The date the match was played, as 2026-10-11. The form takes the date played, even when the schedule shows another. - `lines` (array, required): Each line as the member reports it. - `matchId` (string): USTA NorCal's own id for the match, read from the link on the team page. Optional: it fills in the form's path. - `opponent` (string): The other team in the match, as the schedule names it. With date, or alone. - `posted` (array): Each line as NorCal shows it after the other team entered the score, to compare with the member's record. - `season` (integer): Season year. Defaults to the current season. - `team` (string, required): The member's team: the Desk's team id, which is USTA NorCal's own team id, a link to its team page, or its name. - `weAreHome` (boolean): Whether the member's team was the home team. Read from the schedule when left out. ### `match_date_check` (~402 tokens) A home match date, checked Checks a proposed date and time for a home match before the captain posts it on the USTA NorCal league site. Pass the team, the match and the proposed date and start time, and the format and second-shift time if the captain has them. It says whether the form offers that time, which formats the form offers for the team's lines, and whether the team already plays that day. The Desk never acts on the USTA site, so the captain, or their own agent in their own session, presses Submit. Call it when a captain asks whether a date works, or before an agent fills the post-dates form. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `date` (string): The date the schedule shows for the match now, as 2026-10-24, to find it. Optional with opponent. - `format` (string): The match format, as the form names it: All 3, 2/1 or 1/2 for three lines, and All 5, 3/2, 2/3, 4/1 or 1/4 for five. - `opponent` (string): The other team in the match, as the schedule names it. With date, or alone. - `proposedDate` (string, required): The date the captain wants to post, as 2026-10-24. - `proposedTime` (string, required): The start time the captain wants, as 6:30 PM. - `season` (integer): Season year. Defaults to the current season. - `secondShiftTime` (string): The second shift's start time, for a two-shift format. - `team` (string, required): The member's team: the Desk's team id, which is USTA NorCal's own team id, a link to its team page, or its name. ### `availability_loop` (~454 tokens) Chase who hasn't answered Finds the players who have not answered the next match on the USTA NorCal availability grid. Pass the team and the grid as your agent read it: each match column's header, and each player's row with one cell per column. It lists each player whose answer is blank or maybe, and writes one group message for the team with the deadline and the team grid link. Each line's win chance needs a Desk Pass after the member's free forecast each week. The Desk writes, and the captain sends every message from their own phone or email. Never send a text or an email yourself, and never read a teammate's phone or email. Call it when a captain asks who has not answered on NorCal, or wants reminder texts. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `columns` (array): Each match column's header on the grid, as NorCal prints it, in order, for example #8 Sunday 10/18/26. - `deadline` (string): The answer deadline, as 2026-10-16 1:00 PM. Left out, 48 hours before the match starts. - `format` (string): The match format, as the NorCal post-dates form names it: All 3 or All 5 for one shift, or a split such as 2/1. - `lineupNow` (boolean): Set true to plan the lineup now, before the deadline, from the answers so far. - `matchId` (string): NorCal's own id for the match, from the Line-up link. Optional: it fills in the lineup form's path. - `rows` (array): One row for each player on the grid. - `season` (integer): Season year. Defaults to the current season. - `signAs` (string): The captain's first name, which signs the lineup email. - `team` (string): The team the grid is for: the Desk's team id, which is NorCal's own team id, a link to its team page, or its name. Left out, the signed-in member's own team this season. ### `read_docs` (~259 tokens) Paragraphs from the Desk's docs Reads The Tennis Desk's own docs, word for word. They cover what the Desk is, a Desk level, what is free and what the Desk Pass adds, coverage and updates, agents, privacy and how a league table is ordered. Call it when someone asks about the Desk itself rather than a team, a player or a match. Pass `about`, a few words on what to find, and `pages` for a page you know. It needs no Desk Pass, and a call does not count toward the account's daily or monthly limit. Input parameters: - `about` (string): A few words on what to find, for example 'how it compares with NTRP'. With no `pages`, the sections of any page that match it. - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `pages` (array): One or two docs pages, each named by its address after /docs/, as https://thetennisdesk.com/docs.md lists them, for example 'desk-level'. The front page is 'index'. A page read_docs does not hold is… ### `read_research` (~218 tokens) The Desk's research figures Reads the Desk's published research about players in general, word for word. Each piece comes with its question, headline, answers and figures, the group of past players it counts and the day it was measured. Call it when someone asks about players or teams in general, such as how often players move up or back down, or home advantage. Never call it for one named player, team or match, because every figure is a rate over a group. Pass `about`, a few words on the question, or `pieces` for a piece you know. It needs no Desk Pass. Input parameters: - `about` (string): A few words on the question, for example 'how players do after a bump, and how many move back down'. - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `pieces` (array): One or two pieces, each named by its address after /research/, as https://thetennisdesk.com/research lists them. Optional. ### `query_coverage` (~112 tokens) What the Desk covers Answers what the Desk covers: which areas, leagues, levels, clubs, teams and seasons are on record, and what kinds of question it can answer at all. Call it whenever someone asks what you can look up, what data you have, or which leagues, levels or areas are covered. It takes no arguments, because it reports the whole census rather than a slice of it. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. ### `project_standings` (~287 tokens) How a league could finish Projects how a league table could finish, from the matches left and the Desk's line forecasts. It gives each team's likely place, its chance to finish first and, when the Desk knows the playoff cut, its chance to make the playoffs. It also says what the named team needs, while a Desk Pass adds the team's live playoff report. Call it for a team's playoff chances or what it needs. Pass the team, or `league` and `area` for a whole league, or neither for the member's own team. Needs a Desk Pass. Without one, a call gets the free part, with no chance in it, and `deskPass`, whose `message` you give the person. Input parameters: - `area` (string): The area of that league, e.g. 'Marin'. Used only with `league`. - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `league` (string): A league to project when no team is named, with its words, e.g. "55 & over men's 8.0". Used only without `team`. - `team` (string): The team whose league to project, e.g. 'Belvedere men's 7.5'. Omit for the signed-in member's own team. Or the team's Desk page link or number. ### `query_playoff_history` (~175 tokens) Past playoff chances Gives a team's playoff chances from a week ago and earlier, one a week, each as of its day. It also says what moved the chance most: the change between two days and the matches played between them. Call it for how a team's playoff chances have changed, or what its chances were last week. Pass the team, or nothing for the member's own team. It never gives today's chance: the `project_standings` tool gives that, with the Desk Pass. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `team` (string): The team, e.g. 'Belvedere men's 7.5'. Omit for the signed-in member's own team. Or the team's Desk page link or number. ### `query_forecast_results` (~188 tokens) How past forecasts did Gives a team's latest matches that the Desk forecast before they were played. For each line, it gives the team's chance as the Desk logged it the night before, and whether the team won the line. It also gives each match's result. Call it for how the Desk's forecasts did for a team, or what the Desk gave a team in a past match. Pass the team, or nothing for the member's own team. It gives only matches already played, never a chance for a match still to come, which comes with the Desk Pass. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `team` (string): The team, e.g. 'Belvedere men's 7.5'. Omit for the signed-in member's own team. Or the team's Desk page link or number. ### `scout_team` (~187 tokens) A written scout of one team Writes the Desk's scout of one team it covers: its ranked reads of who matters and how the lines go, each with its evidence. Call it when someone asks for a scout, a breakdown of a team, or how to beat a named team. Pass `team`, a team the Desk covers, by name or Desk page link. Never call it for a whole club, because a scout is of one team. Needs a Desk Pass. Without one, a call gets the free part, with no chance in it, and `deskPass`, whose `message` you give the person. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. - `team` (string, required): The team to scout, e.g. 'Belvedere 18AM3.5A', or its Desk page link or number. ### `get_desk_pass` (~108 tokens) Your Desk Pass and forecasts Says whether the signed-in member holds the Desk Pass, when it renews or ends, how many forecasts they have left this week and when more come. Call it when someone asks about their Desk Pass or their forecasts. It takes no arguments. Needs a signed-in member, because it answers about them. A key with no member gets the error member_required. Input parameters: - `asked` (string): The person's question word for word, never paraphrased. Leave it out rather than invent one. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/chungty-thetennisdesk/api-mcp#diagnostics ## Score history - 2026-11-05: 75 - 2026-11-04: 74 - 2026-11-03: 74 - 2026-11-02: 73 - 2026-11-01: 73 - 2026-10-31: 72 - 2026-10-30: 72 - 2026-10-29: 71 ## Common questions ### What is the The Tennis Desk MCP server? The Tennis Desk is an MCP server listed in the public MCP registry as io.github.chungty/thetennisdesk. Ratings, line win chances and lineup help for USTA NorCal adult league tennis, from public results. This page covers its hosted endpoint (https://thetennisdesk.com/api/mcp). ### Is the The Tennis Desk MCP server safe to use? The Tennis Desk scores 75 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 The Tennis Desk MCP server expose? The Tennis Desk exposes 29 tools: plan_lineup, query_team_record, query_matchup, query_roster, query_player_history, and 24 more. Their descriptions and schemas cost roughly 7,545 tokens of context every time the server is loaded. ### Does the The Tennis Desk MCP server require authentication? No. We connected to The Tennis Desk without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the The Tennis Desk MCP server still maintained? The Tennis Desk is still listed as active in the MCP registry. We last reached this channel on 5 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 The Tennis Desk MCP server? VerifyMCP ran 13 checks on The Tennis Desk, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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://thetennisdesk.com/api/mcp - Website: https://thetennisdesk.com/ - Changelog RSS feed: https://verifymcp.io/servers/chungty-thetennisdesk/api-mcp.xml - Changelog JSON feed: https://verifymcp.io/servers/chungty-thetennisdesk/api-mcp/changelog.json - Trust report (JSON): https://verifymcp.io/servers/chungty-thetennisdesk/api-mcp.json - HTML version of this page: https://verifymcp.io/servers/chungty-thetennisdesk/api-mcp