Manage candidates, jobs, clients, contacts, deals and users in Recruiterflow: search and update the pipeline, add candidates to jobs, move them between stages and log notes.
Recruiterflow ships in the w6w first-party pack. It declares 24 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.recruiterflowRecruiterflow is an applicant tracking system and recruiting CRM for staffing agencies and in-house recruiting teams. This app lets a workflow work the recruiting pipeline: list, fetch and search candidates, jobs, client companies, contacts, deals and users, and read the account’s tags and job stage names.
On the write side it creates and updates candidates, adds a candidate to a job (as Sourced or Applied), moves them between pipeline stages by id or name, disqualifies them with a reason, and logs notes. It also creates contacts and client companies. Search actions accept Recruiterflow’s own filter objects, so any saved-search style query the vendor supports is reachable.
Authentication is a single account API key. Health checks cover API reachability and the key’s liveness; Recruiterflow publishes no status page.
Three routes to the same 24 actions. The Workflow tab is generated from Recruiterflow'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.
candidate-add-to-job Add a candidate to a job; they land in the Sourced stage unless marked applied.
candidate-move-to-stage Move a candidate to a stage of a job, by stage id or by stage name.
candidate-search Search candidates with the filters documented in Recruiterflow's Candidate Search guide.
candidate-update Update a candidate. This is a complete update per key: a key you send replaces the stored value, a key you omit is untouched.
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 Recruiterflow's real ids.
{
"manifestVersion": "2",
"name": "recruiterflow-example",
"steps": [
{
"id": "candidate-add",
"uses": {
"app": "io.w6w.recruiterflow",
"action": "candidate-add",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"name": "<name>"
}
}
]
}candidate-add candidate-add-to-job candidate-disqualify candidate-get candidate-list +19 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 Recruiterflow, 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 Recruiterflow. 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: "candidate-add",
payload: {
name: "<value>",
// email: "<value>",
// title: "<value>",
// organization: "<value>",
// source: "<value>",
// linkedinProfile: "<value>",
// fields: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action candidate-add --payload '{"name":"<value>"}' Give an AI agent Recruiterflow — without giving it Recruiterflow'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.recruiterflow#candidate-add",
"input": {
"name": "<name>"
}
}
}
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 Recruiterflow 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.
Recruiterflow'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. Recruiterflow itself is MIT, and the runtime that executes it is source-available (FSL).
Recruiterflow declares its own checks, so its health is a property of the app rather than something the host guesses at.
Unsigned POST https://api.recruiterflow.com/api/external/info. Recruiterflow's own "Please supply an API key" body (HTTP 400, not 401) passes: it proves the API and its auth layer are answering. Credential validity is the derived `auth:*` check's job.