simple-jira-mcpSAFE
Very light MCP server for Jira Cloud integration with Claude, Gemini, Cursor, and other AI agents
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 that provides Jira Cloud integration for AI agents.
Features
- Search issues using JQL (Jira Query Language)
- Retrieve issue details with comments and attachments
- Create, update, and delete issues
- List available transitions and transition issues with screen fields
- Add comments, including comments posted with a transition
- Download attachments
- Connect to multiple Jira instances
Choosing this server
Use this server to run Jira tools locally with your API token:
- Connect to multiple Jira instances through
JIRA_CONFIG_JSONand select
one with config_id.
- Download attachments to disk.
- Search, read, create, update, delete, transition, and comment on issues
through ten tools.
- Choose search response fields and read descriptions and comments as plain
text.
You install and maintain the server. It supports Jira Cloud and uses the configured API token for each instance. It does not support per-user OAuth or other Atlassian products.
See Atlassian's official MCP server for an alternative.
Requirements
- Python 3.11+
- Jira Cloud account with API token
Installation
git clone https://github.com/timohaa/simple-jira-mcp.git cd simple-jira-mcp python -m venv venv # Linux/macOS source venv/bin/activate # Windows # venv\Scripts\activate pip install -e ".[dev]"
Configuration
Set the JIRA_CONFIG_JSON environment variable with your Jira credentials:
export JIRA_CONFIG_JSON='[
{
"id": "work",
"url": "https://your-domain.atlassian.net",
"email": "[email protected]",
"token": "your-api-token",
"timeout": 60
}
]'Generate an API token at:
Set timeout per instance to limit each HTTP phase in seconds. It defaults to 30 and must be positive. Raise it for slow connections. See [APIREFERENCE.md](APIREFERENCE.md#
3d5c890c2b36OBSERVED · 2026-10-10Connect
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.
claude mcp add simple-jira-mcp -- uvx simple-jira-mcp
{
"mcpServers": {
"simple-jira-mcp": {
"command": "uvx",
"args": [
"simple-jira-mcp"
]
}
}
}Exposed tools (3)
1 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add_comment | write | Add a comment to an issue. |
create_issue | write | Create a new Jira issue. |
download_attachment | read | Download an attachment from a 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 (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (8)
.markdownlint.json
filename="../../etc/passwd.png",
assert sanitize_filename("../../../etc/passwd") == "passwd""JIRA_CONFIG_JSON": "[{\"id\": \"work\", \"url\": \"https://your-domain.atlassian.net\", \"email\": \"[email protected]\", \"token\": \"your-api-token\"}]""JIRA_CONFIG_JSON": "[{\"id\": \"work\", \"url\": \"https://your-domain.atlassian.net\", \"email\": \"[email protected]\", \"token\": \"your-api-token\"}]""JIRA_CONFIG_JSON": "[{\"id\": \"work\", \"url\": \"https://your-domain.atlassian.net\", \"email\": \"[email protected]\", \"token\": \"your-api-token\"}]"JIRA_CONFIG_JSON = '[{"id": "work", "url": "https://your-domain.atlassian.net", "email": "[email protected]", "token": "your-api-token"}]'"JIRA_CONFIG_JSON": "[{\"id\": \"work\", \"url\": \"https://your-domain.atlassian.net\", \"email\": \"[email protected]\", \"token\": \"your-api-token\"}]"Gates applied: no_behavioural_pass.
3d5c890c2b36full audit observations/trust-audit/mcp-server/timohaa__simple-jira-mcp.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 |
|---|---|---|---|---|---|
| 2026-10-10 | 3d5c890c2b36 | SAFE | B | 89 | first audit |
Questions
What is the simple-jira-mcp MCP server?
Very light MCP server for Jira Cloud integration with Claude, Gemini, Cursor, and other AI agents
What tools does simple-jira-mcp expose?
3 in total: 1 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is simple-jira-mcp 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 simple-jira-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (3d5c890c2b36), read on 2026-10-10. The repository is watched and re-audited when it changes.