# Jira connector

[Product](https://paperclip.ing/product/) / [Connectors](https://paperclip.ing/product/connectors/) / Jira

Read issues, add comments and update work items.

Category: [Productivity](/product/connectors/?category=productivity)
Tools from: [Jira](https://support.atlassian.com/atlassian-rovo-mcp-server/docs/supported-tools/)
Sign-in: Choose a supported connection method
Works as: Agent tool

Source recorded: Sep 30, 2026

## Overview

Paperclip’s Jira MCP connector gives your AI agents tools to read issues, add comments and update work items. Each tool can be Allowed, Ask first or Off.

Agents reach issues the authorizing account can access on the selected site, subject to project permissions and issue security. Paperclip has no project picker.

## What agents can do with Jira

- Read an issue before commenting (`getJiraIssue`, `addOrEditJiraIssueComment`)
- Review and update a work item (`getJiraIssue`, `editJiraIssue`)
- Review before changing issue status (`getJiraIssue`, `transitionJiraIssue`)

## How to connect Jira

1. In Paperclip, open Connectors and select Jira.
2. On the Access step, choose the identity and which agents may use the connection.
3. Select Sign in with Jira and authorize in Atlassian’s browser flow. Choose the intended site if Atlassian asks.

[Setup guide](https://docs.paperclip.ing/connectors/jira/)

## Jira tools for agents (11)



### Write (11)

<div data-tool-name="addOrEditJiraIssueComment" data-tool-class="write">
<code>addOrEditJiraIssueComment</code>
<p class="c4-description-summary">Add a comment, or edit an existing one.</p>
</div>

<div data-tool-name="atlassianUserInfo" data-tool-class="write">
<code>atlassianUserInfo</code>
<p class="c4-description-summary">Get the current authenticated user's account information.</p>
</div>

<div data-tool-name="createJiraIssue" data-tool-class="write">
<code>createJiraIssue</code>
<p class="c4-description-summary">Create a new Jira work item.</p>
</div>

<div data-tool-name="discover" data-tool-class="write">
<code>discover</code>
<p class="c4-description-summary">Natural-language search over the deferred tool catalogue.</p>
<details class="faq-item c4-tool-description">
<summary class="faq-header" aria-label="Full description for discover">Full description</summary>

<pre class="faq-answer c4-description-text">Natural-language search over the deferred tool catalogue. Returns a list of potentially related tools, their toolSchema and operations for running on execute.</pre>
</details>
</div>

<div data-tool-name="editJiraIssue" data-tool-class="write">
<code>editJiraIssue</code>
<p class="c4-description-summary">Edit an existing work item; only fields editable on that work item can be set.</p>
</div>

<div data-tool-name="executeDestructive" data-tool-class="write">
<code>executeDestructive</code>
<p class="c4-description-summary">Execution pathway to run any deferred tools identified via discovery.</p>
<details class="faq-item c4-tool-description">
<summary class="faq-header" aria-label="Full description for executeDestructive">Full description</summary>

<pre class="faq-answer c4-description-text">Execution pathway to run any deferred tools identified via discovery. Utilisation of each execute type is used to apply agent-level confirmation.</pre>
</details>
</div>

<div data-tool-name="executeRead" data-tool-class="write">
<code>executeRead</code>
<p class="c4-description-summary">Execution pathway to run any deferred tools identified via discovery.</p>
<details class="faq-item c4-tool-description">
<summary class="faq-header" aria-label="Full description for executeRead">Full description</summary>

<pre class="faq-answer c4-description-text">Execution pathway to run any deferred tools identified via discovery. Utilisation of each execute type is used to apply agent-level confirmation.</pre>
</details>
</div>

<div data-tool-name="executeWrite" data-tool-class="write">
<code>executeWrite</code>
<p class="c4-description-summary">Execution pathway to run any deferred tools identified via discovery.</p>
<details class="faq-item c4-tool-description">
<summary class="faq-header" aria-label="Full description for executeWrite">Full description</summary>

<pre class="faq-answer c4-description-text">Execution pathway to run any deferred tools identified via discovery. Utilisation of each execute type is used to apply agent-level confirmation.</pre>
</details>
</div>

<div data-tool-name="getAccessibleAtlassianResources" data-tool-class="write">
<code>getAccessibleAtlassianResources</code>
<p class="c4-description-summary">List all Atlassian sites and apps accessible to the authenticated user, including their cloudId values.</p>
<details class="faq-item c4-tool-description">
<summary class="faq-header" aria-label="Full description for getAccessibleAtlassianResources">Full description</summary>

<pre class="faq-answer c4-description-text">List all Atlassian sites and apps accessible to the authenticated user, including their cloudId values. Required first call for any tool because every tool call needs a cloudId.</pre>
</details>
</div>

<div data-tool-name="getJiraIssue" data-tool-class="write">
<code>getJiraIssue</code>
<p class="c4-description-summary">Get a Jira work item by ID or key.</p>
</div>

<div data-tool-name="transitionJiraIssue" data-tool-class="write">
<code>transitionJiraIssue</code>
<p class="c4-description-summary">Transition an work item to a new status, and/or assign it to a sprint or backlog.</p>
</div>

This list describes the reviewed tools. Your selected method, provider access and action permissions determine what agents can use.

These lists use a conservative permission policy. Read requires a provider read-only hint or a reviewed Paperclip read rule. Evidence that an action changes data or submits information elsewhere puts it in Write. Write also includes actions we cannot verify as read-only. Read describes the reviewed evidence; it does not guarantee that an action has no side effects. A connected account can group actions differently.

This list includes the provider’s directly exposed Primary tools. Deferred operations and Confluence tools are excluded. executeRead, executeWrite and executeDestructive are provider tools; their individual API operations are not separate tools.



### Connection policies

Discovered actions follow the connection’s policies. Review their permissions and set actions to Ask first or Off as needed. Comments and changes are attributed to the authorizing account.

## Jira connector FAQ

### Can I require approval for actions?

Set an action to Ask first to require human approval of each call or Off to prevent calls. Allowed actions run without approval. Read and Write grouping is separate from these settings.

### What can agents reach in Jira?

Agents reach issues the authorizing account can access on the selected site, subject to project permissions and issue security. Paperclip has no project picker.

### What do I need before connecting?

Use Jira Cloud and an Atlassian account with access to the intended site and projects. Tenant administrators may need to approve the client.


Ways to connect

- Sign in with Jira
  - Use browser sign-in for the provider-hosted server.

[Jira connector](https://docs.paperclip.ing/connectors/jira/)

[Set action permissions](https://docs.paperclip.ing/connectors/action-permissions/)

## Related connectors

- [Arcade](https://paperclip.ing/product/connectors/arcade/): Connect your Arcade gateway.
- [Asana](https://paperclip.ing/product/connectors/asana/): Find tasks, add comments and update task details.
- [Composio](https://paperclip.ing/product/connectors/composio/): Discover app tools and execute authorized actions.

## Give your agents Jira.

Join the Paperclip waitlist to connect Jira and choose what your agents can do.

[Join the waitlist](https://paperclip.ing/waitlist/)