jira

import { jira } from '@agentskit/tools/integrations'

const tools = jira({
  baseUrl: 'https://my-org.atlassian.net',
  email: process.env.JIRA_EMAIL!,
  apiToken: process.env.JIRA_API_TOKEN!,
})

Bundled: jira(config) returns both sub-tools. Calls Jira REST API v3 at your Atlassian site root.

#Sub-tools

#Schema

#jira_search_issues

Returns: key, summary, status, assignee for each match.

#jira_create_issue

Returns: key and url (full Jira link to the created issue).

#Example — sprint assistant

import { createRuntime } from '@agentskit/runtime'
import { jira } from '@agentskit/tools/integrations'

const runtime = createRuntime({
  adapter,
  systemPrompt: 'You manage sprint work. Search for blockers and create follow-up tasks.',
  tools: jira({
    baseUrl: process.env.JIRA_BASE_URL!,
    email: process.env.JIRA_EMAIL!,
    apiToken: process.env.JIRA_API_TOKEN!,
  }),
})

await runtime.run('Find all in-progress issues assigned to alice@example.com in project ENG.')

#Security

• Env vars required: JIRA_EMAIL (Atlassian account email), JIRA_API_TOKEN (Atlassian API token from id.atlassian.com/manage-profile/security/api-tokens), JIRA_BASE_URL (your Atlassian site, e.g. https://my-org.atlassian.net).
• Authentication is HTTP Basic: email:apiToken base64-encoded. Never commit tokens; use env vars or a secrets manager.
• Use a service-account email for production agents rather than a personal Atlassian account.
• Atlassian Cloud enforces rate limits per site; high-volume queries should use maxResults pagination.
• jira_create_issue writes to the project — gate via HITL for autonomous agents.

#Related

• confluence — pair with Jira for full Atlassian coverage.
• Integrations overview