Manage conversations, messages, and contacts on Crisp — customer messaging and support.
Crisp ships in the w6w first-party pack. It declares 12 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.crispCrisp is a customer messaging and support platform — live chat widget, shared inbox, and contact (“people”) CRM in one workspace.
This app covers the core loop a workflow needs: read and list conversations, create a new conversation session, send a chat reply or an internal note, update a conversation’s state (pending/unresolved/resolved) or its visitor metadata (nickname, email, subject, segments), and manage contact profiles (list, get, create, update). It also resolves the connected workspace’s own information, which doubles as the credential-liveness probe.
Crisp’s REST API is much broader than this — helpdesk articles, campaigns, plugin/widget management, buckets and media, call sessions, browsing-assist — none of which is implemented here; see README.md for exactly what was left out and why.
Three routes to the same 12 actions. The Workflow tab is generated from Crisp's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
create-conversation Creates a new, empty conversation session. Send a message to make it visible.
update-conversation-meta Updates a conversation's visitor identity, subject, or segments.
update-conversation-state Marks a conversation as pending, unresolved, or resolved.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Crisp's real ids.
{
"manifestVersion": "2",
"name": "crisp-example",
"steps": [
{
"id": "create-people-profile",
"uses": {
"app": "io.w6w.crisp",
"action": "create-people-profile",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"email": "<email>",
"nickname": "<nickname>"
}
}
]
}create-people-profile create-conversation get-conversation get-people-profile get-website +7 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Crisp, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Crisp. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "create-people-profile",
payload: {
email: "<value>",
nickname: "<value>",
// phone: "<value>",
// address: "<value>",
// companyName: "<value>",
// segments: "<value>",
// notepad: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action create-people-profile --payload '{"email":"<value>","nickname":"<value>"}' Give an AI agent Crisp — without giving it Crisp's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.crisp#create-people-profile",
"input": {
"email": "<email>",
"nickname": "<nickname>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Crisp connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Crisp's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Crisp itself is MIT, and the runtime that executes it is source-available (FSL).
Crisp declares its own checks, so its health is a property of the app rather than something the host guesses at.
Crisp's own Vigil status page (status.crisp.chat), page-level indicator only. Unauthenticated and unsigned.