It's an MCP (Model Context Protocol) server that connects Jira to your AI, giving the agent tools to act on your data, through a single remote link.

Which AI clients does it work with?

Any MCP-compatible client: Claude (web, desktop and mobile), Cursor, ChatGPT with connectors, OpenClaw and other agents.

No. Paste the remote URL into your client, authenticate once, and you're done. No packages to install, no code to write.

Is it secure? Can the AI change my data?

Access is authorized by you and can be revoked anytime. Permissions follow what Jira exposes; you approve them when connecting.

Is my customers' data stored on mcp.ai?

No. Whatever Jira returns passes through our infrastructure solely to reach the AI assistant you chose, and that content is not stored. By design we don't persist tool-call payloads: the log keeps metadata only (which tool, timestamp, status, duration, size and a hash of the arguments). Your credentials are stored encrypted and you can revoke the connection at any time. Retention periods and details are in the Privacy Policy at mcp.ai/privacy.

Is my data used to train AI models?

No. Nothing that flows through the connector is used to train or improve AI models, nor shared with third parties for that purpose. The conversation itself, meaning your prompts and the AI's answers, is processed by the AI provider you choose (Claude, ChatGPT and the like), under their own privacy policy.

How much does it cost?

You start free and upgrade when you need more usage. Billing and limits are managed in your mcp.ai account.

Can I cancel anytime?

Yes. Plans are monthly and can be cancelled at any time, with no lock-in.

Jira MCP Server and REST API

Jira

Jira in natural language: create, search and update issues, transitions, sprints and projects. The platform provides the OAuth app, just click Connect and authorize your Atlassian site. Multiple sites can be connected to the same MCP.

Install in your client

MCP server URL

https://api.mcp.ai/p_jira

Secure connection via OAuth 2.0

Tools (45)

For developers

API & agent docs

Machine-readable docs to plug this server into an agent or call it over REST.

Skill (how to use)

Markdown: use via MCP or via the direct REST API.

Open

llms.txt

Agent-readable spec of this server.

Open

For agents

Install prompt — paste into Claude, ChatGPT, Cursor or any MCP agent and it sets itself up.

Open

Postman collection

Import the REST API into Postman.

Download

Guides

Guides and tutorials

Step-by-step walkthroughs with copy-paste prompts.

Needs your own key

Como oferecer um MCP dentro do seu produto

Cada usuário do seu app conecta a conta dele: connect sessions com client_ref, webhook de conexão, leitura por API e as páginas de conexão no seu domínio.

Guides

Needs your own key

Cada usuário do seu app com o MCP dele

Em vez de consumir a API no seu backend, cada usuário final pluga o MCP dele no Claude/ChatGPT: toolkit e convite por usuário, isolamento de fábrica e a URL no seu domínio.

Guides

FAQ

Jira

Tools (45)

API & agent docs

Guides and tutorials

Como oferecer um MCP dentro do seu produto

Cada usuário do seu app com o MCP dele

Frequently asked questions

Example prompts

Jira

Tools (45)

jira_add_attachmentUploads and attaches a file to a Jira issue.

jira_add_commentAdds a comment using Atlassian Document Format (ADF) for rich text to an existing Jira issue.

jira_add_watcher_to_issueAdds a user to an issue's watcher list by account ID. Requires the authenticated user to have permission to view the issue and manage watchers; insufficient permissions may result in silent failure or

jira_assign_issueAssigns a Jira issue to a user, default assignee, or unassigns; supports email/name lookup.

jira_bulk_create_issueCreates multiple Jira issues (up to 50 per call) with full feature support including markdown, assignee resolution, and priority handling.

jira_create_issueCreates a new Jira issue (e.g., bug, task, story) in a specified project. IMPORTANT: Different Jira projects may have custom required fields beyond the standard ones (summary, project_key, issue_type)

jira_create_issue_linkLinks two Jira issues using a specified link type with optional comment.

jira_create_projectCreates a new Jira project with required lead, template, and type configuration.

jira_create_sprintCreates a new sprint on a Jira board with optional start/end dates and goal.

jira_create_versionCreates a new version for releases or milestones in a Jira project.

jira_delete_commentDeletes a specific comment from a Jira issue using its ID and the issue's ID/key; requires user permission to delete comments on the issue.

jira_delete_issuePermanently and irreversibly deletes a Jira issue by its ID or key. Obtain explicit user confirmation before calling.

jira_delete_versionDeletes a Jira version and optionally reassigns its issues.

jira_delete_worklogDeletes a worklog from a Jira issue with estimate adjustment options.

jira_edit_issueUpdates an existing Jira issue with field values and operations. Supports direct field parameters (summary, description, assignee, priority, etc.) that are merged with the fields parameter. Direct par

jira_find_usersDEPRECATED: Use JIRA_FIND_USERS2 instead. Searches for Jira users by email or display name to find account IDs; essential for assigning issues, adding watchers, and other user-related operations. Broa

jira_get_all_issue_type_schemesRetrieves all Jira issue type schemes with optional filtering and pagination.

jira_get_all_projectsRetrieves all visible projects using the modern paginated Jira API with server-side filtering and pagination support. Results reflect only projects the authenticated user can access — small or empty r

jira_get_all_statusesRetrieves all issue statuses associated with workflows from Jira. Returns global statuses that may not be valid for every project or workflow scheme; verify a returned status is applicable to the spec

jira_get_all_usersRetrieves all users from the Jira instance including active, inactive, app accounts, and system accounts, with pagination support. On Jira Cloud, fields like `email_address` may be redacted due to pri

jira_get_commentRetrieves a specific comment by ID from a Jira issue with optional expansions.

jira_get_current_userRetrieves detailed information about the currently authenticated Jira user. The returned `accountId` is the correct identifier for fields like `lead_account_id` in JIRA_CREATE_PROJECT, JIRA_ADD_WATCHE

jira_get_issueRetrieves a Jira issue by ID or key with customizable fields and expansions. Request only needed fields and expansions to avoid large responses. Use specific `customfield_*` keys in `fields` to verify

jira_get_issue_link_typesRetrieves all configured issue link types from Jira.

jira_get_issue_propertyRetrieves a custom property from a Jira issue by key.

jira_get_issue_resolutionsRetrieves all available issue resolution types from Jira.

jira_get_issue_typesRetrieves all Jira issue types available to the user using the modern API v3 endpoint; results vary based on 'Administer Jira' global or 'Browse projects' project permissions. Response includes two sh

jira_get_issue_watchersRetrieves users watching a Jira issue for update notifications. Watcher data access may be restricted by Jira permissions. Returns all watchers; filter client-side by `accountId` to check if a specifi

jira_get_issue_worklogsDEPRECATED: Use JIRA_GET_WORKLOG instead. This action is deprecated because it lacks the expand parameter for worklog properties. Use JIRA_GET_WORKLOG which provides the same functionality plus the ab

jira_get_project_versionsRetrieves all versions for a Jira project with optional expansion. Use version IDs from the response (not names) when setting fixVersions or affectedVersions on issues — submitting names alone causes

jira_get_remote_issue_linksRetrieves links from a Jira issue to external resources.

jira_get_transitionsRetrieves available workflow transitions for a Jira issue. Always use the numeric `id` from the response when calling JIRA_TRANSITION_ISSUE — transition IDs are project/workflow-specific and must not

jira_get_votesFetches voting details for a Jira issue; requires voting to be enabled in Jira's general settings.

jira_get_worklogRetrieves worklogs for a specified Jira issue.

jira_list_boardsRetrieves paginated Jira boards with filtering and sorting options. Use `start_at` and `max_results` together, looping through pages to retrieve all results.

jira_list_issue_commentsRetrieves paginated comments from a Jira issue with optional ordering. Paginate by incrementing `start_at` by `max_results` until the cumulative count reaches the `total` field in the response. A resp

jira_list_sprintsRetrieves paginated sprints from a Jira board with optional state filtering.

jira_move_issue_to_sprintMoves one or more Jira issues to a specified active sprint.

jira_remove_watcher_from_issueRemoves a user from an issue's watcher list by account ID.

jira_search_for_issues_using_jql_getSearches for Jira issues using JQL with pagination and field selection.

jira_search_for_issues_using_jql_postDEPRECATED: Use JIRA_SEARCH_ISSUES instead. Searches for Jira Cloud issues using Enhanced JQL via POST request; supports eventual consistency and token-based pagination. Use this POST endpoint for lon

jira_search_issuesAdvanced Jira issue search supporting structured filters and raw JQL. At least one filter parameter (e.g., jql, project_key, updated_after) is required; calls with no parameters will be rejected.

jira_send_notification_for_issueSends a customized email notification for a Jira issue.

jira_transition_issueTransitions a Jira issue to a different workflow state, with support for transition name lookup and user assignment by email. IMPORTANT: Only fields that are on the transition's screen can be set duri

jira_update_commentUpdates text content or visibility of an existing Jira comment.

API & agent docs

Guides and tutorials

Como oferecer um MCP dentro do seu produto

Cada usuário do seu app com o MCP dele

Frequently asked questions

What is Jira MCP?

Which AI clients does it work with?

Do I need to code?

Is it secure? Can the AI change my data?

Is my customers' data stored on mcp.ai?

Is my data used to train AI models?

How much does it cost?

Can I cancel anytime?

Example prompts