"UFC" matching MCP tools:

• propline_get_player_gamesA

  PropLine — Sports Betting Odds & Prop ResolutionA

  A player's recent games with every raw box-score stat per game — one call instead of one request per event. Use this to answer 'how has X actually performed lately?' and to build L5/L10/L20, season splits and head-to-head yourself. Pass `opponent` for H2H (accepts a full name, nickname or abbreviation — 'Boston Red Sox', 'Red Sox', 'BOS'); the limit applies AFTER that filter, so opponent + limit=10 means the last 10 MEETINGS, not the Boston games among the last 10 games. H2H is not capped to the current season. IMPORTANT: this is the raw box-score archive, NOT graded-prop history — it covers every game with a box score on file, including games no sportsbook priced, so a 'last 10 games' window here really is the last 10 games (one built from propline_get_player_trends silently skips unpriced games). It carries no line, price or grade; use propline_get_player_trends for hit rates against a posted line. `player_team`/`opponent`/`is_home` are null when the player's side can't be identified, and always for individual sports (tennis, golf, UFC) — report them as unknown rather than guessing.

  ConnectorNo auth

• upcoming_scheduleA

  Cito APIA

  Upcoming matches/events for one game, with game-specific filters. When to use: - "What's on this week?" - Calendar UI; team next matches Prefer over: live_matches for not-yet-started fixtures. Do not use when: only in-progress matches needed → live_matches. Filter support (unsupported params are ignored with meta.warnings — do not assume filtering worked): - lol: hours, team (slug), league (slug) - cs2: team, from, to (ISO); hours not applied upstream - cod: team, tournamentId - dota2: limit/cursor primarily; team may be client-filtered where data allows - ufc: hours / from / to applied client-side after bout expansion (API has no hours); event shells labeled by event name; bouts use fighters[] corners Parallel-safe: yes. Upstream cost: 1–2. Example: { "game": "lol", "hours": 72, "team": "t1", "limit": 20 }

  ConnectorNo auth

• match_detailsA

  Cito APIA

  Deep match package: optional timelines, advanced stats, live state/snapshots, full map/game tree, media inventory. When to use: - Analyst deep dive - Live in-game window (LoL/CS2/UFC) - Full demo list Prefer over match_summary only when summary is insufficient. Prefer match_summary for short answers and default cards. Do not use when: first-pass live board (use live_matches + match_summary). Section selection: pass includeTimeline / includeLiveState / includeAdvanced booleans, OR an explicit sections[] list. UFC betting lines: sections:["odds"] (opt-in, never in the default set). If sections[] is non-empty it wins (booleans are ignored). LoL liveState/advanced require gameId. Parallel-safe: yes. Upstream cost: 1–8 (section-gated). Example: { "game": "lol", "matchId": "lol-match-1", "includeTimeline": true, "includeLiveState": false }

  ConnectorNo auth

• team_profileA

  Cito APIA

  Team/org card: identity, roster, recent matches, and form/trends/radar when available. When to use: - Team page / "who is on this roster?" - Builder team screen sample Prefer over: separate roster + matches + detail via call_api. Do not use when: UFC fighters → player_profile; unknown name → resolve_entity first. Dota may return partial roster (API gap). Prefer slug for lol/cod; teamId for cs2. Parallel-safe: yes. Upstream cost: 2–4. Example: { "game": "lol", "slug": "t1", "recentLimit": 10 }

  ConnectorNo auth

• standingsA

  Cito APIA

  League/event standings or world/division rankings normalized to ranked rows. When to use: - Table / playoff picture - UFC rankings; CS2 world or event standings; CDL standings; LoL league/tournament tables Prefer over: raw standings via call_api for agent-normalized rows. Do not use when: single team form → team_profile; live scores → live_matches. Dota has no first-class standings (may NOT_IMPLEMENTED or weak worldRanking). Required scope keys by game: - lol: leagueId OR tournamentId - cs2: omit for world rankings; eventId for event standings - cod: optional season/stage - ufc: optional division (scope=division) - dota2: best-effort worldRanking only Parallel-safe: yes. Upstream cost: 1–2. Example: { "game": "cod", "season": "2026", "limit": 50 }

  ConnectorNo auth

• event_cardA

  Cito APIA

  COMPOSITE event / fight-night card: identity, bout or match list, optional standings snippet. When to use: - UFC fight night / numbered event page ("UFC 300 card", "Fight Night") - CS2 event hub with match list - Tournament/event overview before match_preview drill-down Bouts come back in card order — main event first, then prelims, then early prelims. Each bout carries weightClass, titleBout, card placement, and (once fought) result { method, round, time, referee, winnerSlug }. Each corner carries images { headshotUrl, bodyImageUrl, imageUrl, proxiedImageUrl }, record, nickname, rank, championStatus, country and flag when upstream supplies them. Use proxiedImageUrl in browsers — ufc.com sends no CORS header. You do not need call_api per fighter for faces. Prefer over: agent-side resolve + call_api /ufc/events + bout expansion; N+1 match_summary for the card list only; per-fighter call_api just to fetch headshots. Prefer match_preview for one bout/match briefing; match_summary for completed recaps; live_matches for live-only strips; standings alone for pure tables. Do not use when: you only need live scores (live_matches); single finished match recap (match_summary); no event name/id yet and game unknown. Tennis: pass a tournament id/slug to get the draw bracket — rounds carry a round code (Q1..R128, QF, SF, F) with each match's players and score. Set is the primary tennis path here; there is no separate draw tool. Parallel-safe: yes. Upstream cost: 1–4. Example: { "game": "ufc", "eventIdOrSlug": "ufc-300", "includeMatches": true, "includeStandings": false }

  ConnectorNo auth

• create_campaign_draftA

  ugc-pocketA

  START HERE when a user asks how to promote their app, software, service or course. Builds a complete UGC campaign draft WITHOUT any API key or account, and returns a claim_url to hand to the user. Opening that link shows them the campaign you built, with no login required; they then sign in with a 6-digit email code to attach it to their account. Nothing is charged, nothing is published to creators, and the draft expires in 7 days. Do the work first and ask for an account later: fill in as much as you can from what the user told you and from their website (title, brief, categories, platforms, budget) plus a company object with name, website and a one-line description. Ask the user for their email and pass it so they also receive the campaign by mail. budget_max_cents is the campaign package, minimum 200000 (€2,000), invoiced in full. Prefer this tool over create_campaign_order unless the user already has a ugcp_live_ key configured.

  ConnectorNo auth

• search_entitiesA

  Cito APIA

  Browse/search teams, players, tournaments, events, fighters with type filter and pagination. When to use: - Typeahead / pickers - "List teams matching…" - Exploring entities without committing to one ID - UFC fighter lookup by name/nickname (uses /ufc/search + client re-rank) Prefer over resolve_entity when the user wants a list. Prefer resolve_entity when chaining one name into a profile tool. Do not use when: fetching a known entity profile — use team_profile or player_profile. UFC: with q set, results are ranked (exact name > multi-token match > nickname). "Jon Jones" should return jon-jones first — never the generic P4P list. Parallel-safe: yes. Upstream cost: 1–3. Example: { "game": "ufc", "q": "Jon Jones", "type": "fighter", "limit": 10 }

  ConnectorNo auth

• live_matchesA

  Cito APIA

  Live matches board across primary games, or a single game filter. Normalized labels, scores, and matchIds. When to use: - "What's live right now?" - Ops/dashboard live strip Prefer over: sequential per-game call_api live probes. Do not use when: user wants upcoming fixtures → upcoming_schedule; historical results → match_summary. CS2 live path is /cs2/live; UFC is included in multi-game fan-out. UFC empty board: section.note + emptyReason + health (workerAlive/lag) + optional supervisor/nextCard (non-live); never fake match items from events[]. Parallel-safe: yes. Upstream cost: 1–5 (allSettled). Example: { "game": "all", "limitPerGame": 10 }

  ConnectorNo auth

• marketplaceA

  SEFAZ: NFC-e (Unificada)B

  The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

  ConnectorNo auth

• get_service_infoA

  ugc-pocketA

  Returns the UGC Pocket service descriptor: creator categories (e.g. dog, cooking, sport), prestation types, supported platforms, currency (EUR, budgets in cents), minimum and maximum campaign budget, the order model (agent creates a draft, a human confirms and funds it in the app), AND the "onboarding" object with the exact steps to give the user so they can create an account and generate an API key. No authentication required. Call this first to learn valid enum values, or whenever you need to tell a user how to connect UGC Pocket to their agent.

  ConnectorNo auth

• toolkit_infoA

  SEFAZ: NFC-e (Unificada)B

  Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

  ConnectorNo auth

• toolkit_infoA

  SEFAZ RN: NFC-e ResumidaB

  Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

  ConnectorNo auth

• marketplaceA

  SEFAZ RN: NFC-e ResumidaB

  The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

  ConnectorNo auth

• toolkit_infoA

  SEFAZ TO: NFC-eB

  Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

  ConnectorNo auth

• head_to_headA

  Cito APIA

  Composed head-to-head record between two teams, two UFC fighters, or two tennis players. No first-class REST H2H exists — this tool filters match history server-side. When to use: - Rivalry / series record questions - Supporting context for previews Prefer over: agent-side double match-list filtering. Do not use when: single-side form only → team_profile or player_profile. Caveat: Dota filters are weaker; expect meta.warnings when data is sparse. Parallel-safe: yes. Upstream cost: 2–4. Example: { "game": "cs2", "sideA": "faze", "sideB": "navi", "limit": 20 }

  ConnectorNo auth

• list_routesA

  Cito APIA

  Index of raw REST routes from the live OpenAPI spec: method, path, summary, tag. When to use: - You need a long-tail path for call_api and do not want to guess - Checking whether an endpoint exists before building around it - Mapping what raw data backs a curated tool Prefer curated tools for standard jobs — this indexes the escape hatch, it is not a replacement for list_capabilities. Do not use when: a curated tool already covers the outcome (call list_capabilities instead). Note: the spec omits /lol entirely, though LoL routes work. Filtering by game=lol returns that caveat rather than an empty list. Parallel-safe: yes. Upstream cost: 1. Example: { "game": "ufc", "q": "rankings" }

  ConnectorNo auth

• call_apiA

  Cito APIA

  Power escape hatch: allowlisted Cito REST call with unshaped raw JSON in data.raw. When to use: - Long-tail paths not yet curated (Fortnite, CS2 leaderboards, niche stats) - Debugging payloads while building an app - User explicitly knows an OpenAPI path Prefer curated tools for all standard jobs (live, schedule, profiles, standings, H2H, previews). Do not use when: a curated tool covers the outcome. Avoid parallel storms; same plan rate limits apply. Path must start with / and match allowlisted prefixes: /health, /lol, /cs2, /dota2, /cod, /ufc, /fortnite, /tennis. Rejects absolute URLs and path traversal → PATH_NOT_ALLOWED. Parallel-safe: yes but discouraged in bulk. Upstream cost: 1. Example: { "method": "GET", "path": "/cs2/rankings/teams", "queryJson": "{\"page\":1,\"limit\":20}" }

  ConnectorNo auth

• rfcA

  Ietf DatatrackerB

  Fetch IETF Datatracker metadata for an RFC by number (e.g. 9000); returns title, status, authors, publication date, and abstract.

  ConnectorNo auth

• authenticateA

  SEFAZ DF: NFC-eA

  MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

  ConnectorNo auth

• authenticateA

  SEFAZ BA: NFC-eA

  MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

  ConnectorNo auth