Create, search and transition Jira issues, and manage comments, users and projects.
Jira ships in the w6w first-party pack. It declares 15 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.jiraJira creates, searches and moves issues through their workflow from outside Jira itself — creating and updating issues, assigning them, and transitioning them between statuses after first reading which transitions are actually available from an issue’s current state, rather than guessing at a status name that may not apply.
Comments are a full create/list/delete surface, and issues can be searched with JQL to find exactly the set a workflow needs to act on rather than paging through everything in a project. Projects and users round it out — both can be listed or looked up individually, and users can be searched by name, which matters for resolving who to assign an issue to.
A fit for filing issues from an external event — a bug report, a support escalation, a form submission — and for moving work through a Jira workflow driven by something happening outside Jira.
Three routes to the same 15 actions. The Workflow tab is generated from Jira'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.
issue-delete Permanently delete an issue. Jira has no trash — prefer transitioning it to Done unless you mean it.
issue-get-transitions List the workflow transitions available from the issue's CURRENT status — the ids `issue-transition` needs.
issue-transition Move an issue through its workflow. Status is not directly writable — use `issue-get-transitions` to find the id.
issue-update Update an issue's fields. Jira answers 204 with no body — use `issue-get` to read the result back. Changing status is `issue-transition`.
project-get-many List the projects the connection can see — the source of project keys.
user-search Find users by name or email. Returns account ids — the only identifier Jira's API accepts.
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 Jira's real ids.
{
"manifestVersion": "2",
"name": "jira-example",
"steps": [
{
"id": "comment-add",
"uses": {
"app": "io.w6w.jira",
"action": "comment-add",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"issueKey": "<issueKey>",
"body": "<body>"
}
}
]
}comment-add comment-get-many issue-assign issue-create issue-get +10 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 Jira, 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 Jira. 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: "issue-create",
payload: {
projectKey: "<value>",
issueType: "<value>",
summary: "<value>",
// description: "<value>",
// assigneeId: "<value>",
// priority: "<value>",
// labels: "<value>",
// parentKey: "<value>",
// additionalFields: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action issue-create --payload '{"projectKey":"<value>","issueType":"<value>","summary":"<value>"}' Give an AI agent Jira — without giving it Jira'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.jira#comment-add",
"input": {
"issueKey": "<issueKey>",
"body": "<body>"
}
}
}
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 Jira 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.
Jira'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. Jira itself is MIT, and the runtime that executes it is source-available (FSL).
Jira declares its own checks, so its health is a property of the app rather than something the host guesses at.
Atlassian Statuspage rollup for jira-software.status.atlassian.com, with per-component detail. Unauthenticated and unsigned.
Unauthenticated `GET /status` against this connection's Atlassian site — proves the site exists and is serving.