EVO Academia

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.

Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

Read group activities/classes (turmas). Actions: list — list activities offered schedule — class schedule / available spots (filter by date) [Flattened action: list]

Read group activities/classes (turmas). Actions: list — list activities offered schedule — class schedule / available spots (filter by date) [Flattened action: schedule]

Enroll a member in a class or change an enrollment status. Actions: enroll — enroll a member into a scheduled class change_status — change an enrollment's status (e.g. attended/cancelled) [Flattened action: change_status]

Enroll a member in a class or change an enrollment status. Actions: enroll — enroll a member into a scheduled class change_status — change an enrollment's status (e.g. attended/cancelled) [Flattened action: enroll]

List the gym's bank accounts.

Get the gym/branch configuration (name, timezone, gateway, occupation, card flags).

List gym employees/staff.

List gym entries (check-ins / turnstile access), optionally by member and date range. Bulk support: accepts member_ids for batched execution.

Count of active members (drives the billing tier). Returns { active, total }.

List all EVO gyms/branches linked to this install. Returns each account's id, dns, label, and an "is_default" flag (true when only one is linked). When multiple are linked, every other evo_* tool accepts an optional `account` parameter; pass id, dns, or label (full or partial).

Read gym members. Actions: list — search/paginate members (filter by name/email/document/status) get — fetch one or more members by id (member_ids) [Flattened action: get]

Read gym members. Actions: list — search/paginate members (filter by name/email/document/status) get — fetch one or more members by id (member_ids) [Flattened action: list]

List membership plans (planos) offered by the gym.

List prospects/leads (CRM).

Create or update a prospect/lead. Actions: create — new prospect (name + at least one contact) update — edit an existing prospect (requires id_prospect) [Flattened action: create]

Create or update a prospect/lead. Actions: create — new prospect (name + at least one contact) update — edit an existing prospect (requires id_prospect) [Flattened action: update]

List receivables (contas a receber). Filter by date/status (PROBE: confirm param names). Bulk support: accepts member_ids for batched execution.

Mark a receivable as received/paid. PROBE: confirm body shape with a live gym.

List sales (vendas) over a date range.

Create a sale (e.g. sell a membership/plan to a member). PROBE: confirm body shape.

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.

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

Show the current MCP platform and adapter versions.

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