Jira · Productivity
JIRA_CREATE_ISSUE
Create a Jira issue. Use only after explicit user approval. Returns { id, key, self }.
- Provider
- Jira
- Access
- Write
- Category
- Productivity
- Version
- v1
Input schema
{
"type": "object",
"properties": {
"projectKey": {
"type": "string",
"description": "Project key the issue belongs to, e.g. PROJ."
},
"summary": {
"type": "string",
"description": "Issue summary / title."
},
"issueType": {
"type": "string",
"description": "Issue type name (default Task)."
},
"description": {
"type": "string",
"description": "Optional plain-text description (wrapped in ADF)."
}
},
"required": [
"projectKey",
"summary"
],
"additionalProperties": false
}How to call it
Expose this tool to any MCP-capable agent (Claude, GPT, or your own) through CybrLink's MCP server. The agent calls jira_create_issue with arguments matching the schema above.
CybrLink validates the input, injects the connected Jira credentials server-side, and runs a single scoped provider API call through the shared proxy — the same guarded path as the generic call_api tool. The raw secret never reaches the model, and the response is trimmed to just the fields the agent needs.
Write action — gate behind explicit user approval and write scope.
Frequently asked
- How do I let an AI agent jira create issue?
- Connect Jira to CybrLink, then expose the `jira_create_issue` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Jira credential server-side and runs one scoped API call. Create a Jira issue. Use only after explicit user approval. Returns { id, key, self }.
- Does the AI model see my Jira credentials when using JIRA_CREATE_ISSUE?
- No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can take this action in Jira without the OAuth token or API key ever entering its context.