JiraSAFE
A Model Context Protocol server for Jira.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server implementation that provides access to JIRA data with relationship tracking, optimized data payloads, and data cleaning for AI context windows.
i️ There is a separate MCP server for Confluence
Jira Cloud & Jira Server (Data Center) Support
This MCP server supports both Jira Cloud and Jira Server (Data Center) instances. You can select which type to use by setting the JIRA_TYPE environment variable:
cloud(default): For Jira Cloud (Atlassian-hosted)server: For Jira Server/Data Center (self-hosted)
The server will automatically use the correct API version and authentication method for the selected type.
Features
- Search JIRA issues using JQL (maximum 50 results per request)
- Retrieve epic children with comment history and optimized payloads (maximum 100 issues per request)
- Get detailed issue information including comments and related issues
- Create, update, and manage JIRA issues
- Add comments to issues
- Extract issue mentions from Atlassian Document Format
- Track issue relationships (mentions, links, parent/child, epics)
- Clean and transform rich JIRA content for AI context efficiency
- Support for file attachments with secure multipart upload handling
- Supports both Jira Cloud and Jira Server (Data Center) APIs
Prerequisites
- Bun (v1.0.0 or higher)
- JIRA account with API access
Environment Variables
JIRA_API_TOKEN=your_api_token # API token for Cloud, PAT or password for Server/DC JIRA_BASE_URL=your_jira_instance_url # e.g., https://your-domain.atlassian.net JIRA_USER_EMAIL=your_email # Your Jira account email JIRA_TYPE=cloud # 'cloud' or 'server' (optional, defaults to 'cloud') JIRA_AUTH_TYPE=basic # 'basic' or 'bearer' (optional, defaults to 'basic')
Authentication Methods
- Jira Cloud:
17ae66530af9OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add jira-mcp --env JIRA_API_TOKEN=${JIRA_API_TOKEN} --env JIRA_AUTH_TYPE=${JIRA_AUTH_TYPE} -- npx -y [email protected]{
"mcpServers": {
"jira-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"JIRA_API_TOKEN": "${JIRA_API_TOKEN}",
"JIRA_AUTH_TYPE": "${JIRA_AUTH_TYPE}"
}
}
}
}Exposed tools (9)
5 read · 4 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add_attachment | write | Add a file attachment to a JIRA issue |
add_comment | write | Add a comment to a JIRA issue |
create_issue | write | Create a new JIRA issue |
get_epic_children | read | Get all child issues in an epic including their comments |
get_issue | read | Get detailed information about a specific JIRA issue including comments |
get_transitions | read | Get available status transitions for a JIRA issue |
search_issues | read | Search JIRA issues using JQL |
transition_issue | read | Change the status of a JIRA issue by performing a transition |
update_issue | write | Update an existing JIRA issue |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, typescript, @types/node, bun-types, vite, vite-plugin-dts
Gates applied: no_behavioural_pass.
17ae66530af9full audit observations/trust-audit/mcp-server/cosmix__jira-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 17ae66530af9 | SAFE | B | 89 | first audit |
Questions
What is the Jira MCP server?
A Model Context Protocol server for Jira.
What tools does Jira expose?
9 in total: 5 read-only, 4 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Jira safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Jira need?
It reads JIRA_API_TOKEN and JIRA_AUTH_TYPE from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Jira run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as jira-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (17ae66530af9), read on 2026-10-08. The repository is watched and re-audited when it changes.