CtrlK
BlogDocsLog inGet started
Tessl Logo

atlassian-mcp

Integrates with Atlassian products to manage project tracking and documentation via MCP protocol. Use when querying Jira issues with JQL filters, creating and updating tickets with custom fields, searching or editing Confluence pages with CQL, managing sprints and backlogs, setting up MCP server authentication, syncing documentation, or debugging Atlassian API integrations.

95

1.12x
Quality

100%

Does it follow best practices?

Impact

90%

1.12x

Average score across 6 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Evaluation results

100%

Atlassian MCP Server Setup for Engineering Team

MCP server configuration

Criteria
Without context
With context

sooperset server chosen

100%

100%

uvx/uv installation

100%

100%

Confluence /wiki suffix

100%

100%

No hardcoded secrets

100%

100%

env.example has no real secrets

100%

100%

Correct env variable names

100%

100%

Permission scopes documented

100%

100%

Single auth method

100%

100%

JIRA_URL no /wiki suffix

100%

100%

mcpServers config structure

100%

100%

91%

-2%

Jira Issue Audit Tool for Engineering Teams

Pagination and rate-limit handling

Criteria
Without context
With context

Pagination loop

100%

100%

Pagination termination condition

100%

100%

Rate limit handling

90%

100%

Exponential backoff

100%

100%

No hardcoded credentials

100%

100%

API call logging

100%

100%

No sensitive data in logs

100%

100%

JQL quote correctness

100%

62%

ORDER BY direction

100%

100%

Max results per page

100%

100%

Delay between bulk calls

0%

0%

Error recovery retry count

100%

100%

100%

31%

Database Migration Dependency Tracker

Issue link direction semantics

Criteria
Without context
With context

inward_issue_key is blocker

0%

100%

outward_issue_key is blocked

0%

100%

Correct link_type value

87%

100%

Delay between link calls

100%

100%

Input validation

100%

100%

No hardcoded credentials

100%

100%

Confirmation before write

100%

100%

All three links created

100%

100%

Link result summary

100%

100%

Data-driven chain

100%

100%

63%

8%

Sprint Readiness Checker

JQL probe validation and read-only permission check

Criteria
Without context
With context

maxResults=1 probe

0%

0%

Read-only permission check

0%

0%

Confirmation before bulk

0%

0%

API call logging

50%

100%

No sensitive data in logs

100%

100%

Credentials from env vars

100%

100%

ORDER BY direction

100%

100%

Multi-word JQL quoting

100%

100%

Error recovery

100%

100%

Pagination or bounded results

100%

100%

README permission scopes

66%

100%

100%

Team Issue Dashboard Authentication

OAuth 2.1 authentication with minimal scopes

Criteria
Without context
With context

OAuth 2.1 flow used

100%

100%

No Basic Auth

100%

100%

Minimal scope justification

100%

100%

No localStorage recommendation

100%

100%

Production secrets storage

100%

100%

Token refresh implementation

100%

100%

Token expiry check

100%

100%

Accessible resources lookup

100%

100%

No hardcoded client secrets

100%

100%

State parameter used

100%

100%

89%

23%

Confluence Documentation Reporter

Input sanitization and required field validation

Criteria
Without context
With context

CQL input sanitization

0%

100%

Required field validation before Jira create

0%

35%

No page content in logs

100%

100%

API call logging

100%

100%

Credentials from env vars

100%

100%

CQL uses text~ for search

100%

100%

Error handling on Jira create

75%

75%

CQL specifies space

100%

100%

doc-report.json output

100%

100%

Paginated or bounded results

100%

100%

Repository
jeffallan/claude-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.