Crevio

An AI agent that runs your online business: products, orders, customers, email, and sites.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    An AI agent that runs your online business: products, orders, customers, email, and sites.

    How to connect

    How to connect Crevio to Claude

    The server address to paste into Claude settings:

    https://mcp.crevio.co/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect Crevio to ChatGPT

    The server address to paste into ChatGPT settings:

    https://mcp.crevio.co/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect Crevio to Cursor

    The server address to paste into Cursor settings:

    https://mcp.crevio.co/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (14)

    Raw names from tools/list. Only developers need these.

    whoamiIdentify the account, user, and credential behind this connection, with plan, credit balance, rate limits, and the tools available. Call it first to verify the setup.
    ask_crevioDelegate a job to the Crevio agent and wait for the result. Starts a run that works your account through the Crevio API (products, customers, orders, email, socials, sites, research), waits up to timeout_seconds, and returns the run with the agent's final reply in `result`. For anything longer, use start_task and wait_for_run.
    start_chatOpen a chat with the Crevio agent and queue a run, without waiting. Returns the run immediately — its `chat_id` is the conversation to continue with send_message. Follow the run with wait_for_run or get_run.
    list_chatsList the account's chats, newest first.
    get_chatGet a chat's title, kind, and latest run.
    send_messageContinue a chat with follow-up instructions or answers — the agent keeps its context. Resumes a run waiting in needs_input, or queues a new run when the last one finished. Returns run_busy while a run is still in progress. Optionally waits for the reply.
    list_messagesRead a chat's messages, oldest first. Returns the most recent `limit` messages; page back through older ones with starting_after.
    wait_for_runWait for a run to settle (completed, failed, or needs_input) and return it with the agent's final reply. Returns wait_timed_out if it is still running when the timeout passes; call again.
    get_runFetch a run's current status, summary, pending approvals, and (once settled) the agent's final reply.
    list_runsList the account's task runs, newest first — delegated jobs and scheduled tasks alike. Filter by status or task.
    resolve_approvalsApprove or deny the integration actions a run is paused on (status needs_input with pending_approval_ids). Submit a decision for every pending id at once; the run resumes in the background.
    cancel_runStop a run that is pending, running, or waiting for input. The run is finalized as failed with 'Cancelled by the caller'.
    api_searchDiscover available Crevio API endpoints. Use this BEFORE `api_execute` when you're unsure which endpoint to call, need to check parameter names, or want to explore what's available for a domain (e.g. "experiences", "discounts"). A `tools` method returns the full API catalog — an array of hashes keyed with strings: "method", "path", "summary", "description", "tags", "parameters", "request_body". Examples: `tools.select { |t| t["tags"]&.include?("Products") }.map { |t| "#{t["method"]} #{t["path"]} — #{t["summary"]}" }` `tools.find { |t| t["path"].include?("price_variants") && t["method"] == "POST" }["request_body"]` `tools.map { |t| t["tags"] }.flatten.compact.uniq.sort` — list all API domains
    api_executeExecute Ruby in a sandboxed VM against the Crevio REST API. Use `api_search` first to find the endpoint and its body fields, then call it here. Chain calls, transform results, return the final expression. ## Available in your code ``` get(path, params = {}) # paths auto-prefixed with /v1, routed in-process post(path, **body) # body as keyword args or a hash — both work patch(path, **body) delete(path) find_endpoints(query) # -> ["METHOD /path — summary", ...] iso8601(offset_seconds = 0) # mruby Time has no strftime/iso8601 ``` Returns the **last expression**; `puts` is side-channel only. Every run answers `{result:, calls:, output:}` — `calls` audits each REST call (`method`, `path`, `status`, plus `error_code`/`param` on failure). When `result` has unexpected nils, read `calls` for a non-2xx. Never project only success fields (`{id: r["id"]}`) — that hides the error from `result`. ## Rules that the schema does not tell you - Params are unwrapped, Stripe-style: fields at the TOP level. `{product: {...}}` is silently dropped by most endpoints. - Associations take the bare resource name and a prefix_id string — `product: "prod_x"`, never `product_id:`. Some required ones never appear in a schema's `properties`. - Courses and content live under `/experiences`, NOT `/products`. - Lists answer `{object: "list", data: [...], has_more}`; single resources answer the object directly. - Connected integrations go through the same REST surface: `post("/connections/<id>/execute", tool: "<tool>", arguments: {...})`, with ids from `get("/connections", search: "<service>")`. - Sandboxed mruby: no `File`, `ENV`, `Net::HTTP`, `Process`. 10s, 10 MB. ## Example — publishing a product (the ordering trap) A product cannot be created active: it needs a price variant first, or the call 422s. ```ruby product = post("/products", name: "...") post("/price_variants", product: product["id"], name: "Standard", amount_type: "fixed", amount: 4900, currency: "u