Name: RD Station CRM
Author: w6w

RD Station CRM ships in the w6w first-party pack. It declares 10 actions, 1 health check, and the host runs its code in a sandbox that never sees the credential.

Build with RD Station CRM

Three routes to the same 10 actions. The Workflow tab is generated from RD Station CRM'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.

Actions Workflow Code MCP

Create Contact

create-contact

Create a contact in RD Station CRM.

Create Deal

create-deal

Create a deal in RD Station CRM, optionally linked to an organization and a campaign.

Create Organization

create-organization

Create an organization in RD Station CRM.

Get Contact

get-contact

Fetch one CRM contact by its id.

List Contacts

list-contacts

List CRM contacts with the documented paging, ordering and filters.

List Deal Pipelines

list-deal-pipelines

List the CRM's deal pipelines and their stages.

List Deals

list-deals

List CRM deals with the documented paging, ordering and filters.

List Organizations

list-organizations

List CRM organizations with the documented paging, ordering and filters.

List Users

list-users

List the CRM's users, optionally filtered by enabled/disabled state.

Update Contact

update-contact

Replace the fields of an existing RD Station CRM contact.

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 RD Station CRM's real ids.

{
  "manifestVersion": "2",
  "name": "rdstation-example",
  "steps": [
    {
      "id": "get-contact",
      "uses": {
        "app": "io.w6w.rdstation",
        "action": "get-contact",
        "connection": "conn_YOUR_CONNECTION_ID"
      },
      "with": {
        "contactId": "<contactId>"
      }
    }
  ]
}

Here are some of the things you can do

Get Contact
read
get-contact
Create Contact
perform
create-contact
Create Deal
perform
create-deal
Create Organization
perform
create-organization
List Contacts
search
list-contacts

+5 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 RD Station CRM, 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 RD Station CRM. The Workflow tab is where this app's real ids are.

JS SDK CLI

Install

npm yarn pnpm deno

npm install @w6w/sdk

yarn add @w6w/sdk

pnpm add @w6w/sdk

deno add npm:@w6w/sdk

Code

import { 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: "get-contact",
  payload: {
    contactId: "<value>",
  },
});

if (isActionRun(envelope)) console.log(envelope.value);

Install the CLI

npm install -g @w6w/cli

CLI

w6w run conn_YOUR_CONNECTION_ID --action get-contact --payload '{"contactId":"<value>"}'

Give an AI agent RD Station CRM — without giving it RD Station CRM'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.rdstation#get-contact",
    "input": {
      "contactId": "<contactId>"
    }
  }
}

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 RD Station CRM connections to sign with, and refuses rather than guesses when the answer is ambiguous.

What the agent gets

Credentials it can't read

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.

A tool surface scoped to the caller

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.

A durable workflow in one call

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.

Health-aware discovery

RD Station CRM'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. RD Station CRM itself is MIT, and the runtime that executes it is source-available (FSL).

Request MCP access

Health checks

RD Station CRM declares its own checks, so its health is a property of the app rather than something the host guesses at.

service

RD Station platform status

Reads status.rdstation.com's incident.io RSS feed for open incidents. Informational: the page covers RD Station's whole product suite, not the CRM v1 API this app calls.

RD Station CRM

About