Back to catalog
Human reviewedDevelopment

Skill dossier

atlassian-mcp

Source declaration

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.

The author's original description, preserved in English. It describes intent, not verified performance.

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.

developmentreferences

Research summary

Human reviewed

Skill Atlas editorial review · editorial-preview-1.0.0

Covers working with Jira and Confluence through MCP servers: choosing a server, authenticating, writing JQL and CQL, and running read-first, confirm-before-write workflows.

Review scope

Deterministic static analysis of collected SKILL.md and supporting text/code. Machine-assisted candidates and findings await human editorial review; no dynamic behavior or effect is assessed.

Observable capabilities

  • Selects between the official cloud server, an open-source server or a self-hosted one.
  • Configures OAuth, API token or personal-access-token authentication without hardcoding credentials.
  • Writes and validates JQL and CQL queries with a maxResults=1 probe before full execution.
  • Verifies permissions with a read-only probe and confirms before write or bulk operations.

Limitations & scope

  • Needs a reachable Atlassian instance and valid credentials, which this review did not test.
  • Tool names differ between MCP servers, so the setup reference must be consulted.
  • Example server URLs and sample JQL are illustrative and may need adapting to your site.

Relevant for

  • Teams automating Jira and Confluence workflows
  • Developers debugging Atlassian API integrations
  • Admins choosing between cloud and Data Center MCP servers

What ships with the skill

The file inventory comes from the collected source at the recorded commit. Paths and sizes are structural observations, not a measure of quality.

files
6
Markdown files
6
scripts
0
references
5
Size
74.1 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/atlassian-mcp/references/authentication-patterns.mdReference13.1 KB
skills/atlassian-mcp/references/common-workflows.mdReference18.4 KB
skills/atlassian-mcp/references/confluence-operations.mdReference12.4 KB
skills/atlassian-mcp/references/jira-queries.mdReference12.3 KB
skills/atlassian-mcp/references/mcp-server-setup.mdReference12.4 KB
skills/atlassian-mcp/SKILL.mdInstruction5.4 KB

SKILL.md frontmatter

{
  "name": "atlassian-mcp",
  "description": "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.",
  "license": "MIT",
  "metadata": {
    "author": "https://github.com/Jeffallan",
    "company": "https://synergetic.solutions",
    "version": "1.2.0",
    "domain": "platform",
    "triggers": "Jira, Confluence, Atlassian, MCP, tickets, issues, wiki, JQL, CQL, sprint, backlog, project management",
    "role": "expert",
    "scope": "implementation",
    "output-format": "code",
    "related-skills": "mcp-developer, api-designer, security-reviewer"
  }
}

A reading of the operating sequence

This workflow reconstructs the apparent sequence from source material. Unless controlled evaluation is explicitly recorded, it is provisional—not an observed trace.

  1. 01
    Input

    Select the server

    Choose the official cloud, open-source or self-hosted MCP server.

  2. 02
    Action

    Design queries

    Write JQL for Jira and CQL for Confluence, validating with maxResults=1 before full execution.

  3. 03
    Decision

    Verify permissions

    Confirm required scopes with a read-only probe before any write or bulk operation.

  4. 04
    Output

    Deliver configuration and calls

    Provide server configuration, query examples, tool calls with error handling and permission notes.

Potential risk surfaces

Static findings identify points to inspect before installation. They do not establish that a skill is safe, malicious, or effective.

Attention recommended

235 deterministic lexical finding(s) require review across the collected text. Findings can occur in documentation and do not prove execution or exploitability; binary-only files were not scanned.

Network accessObserved
File writesObserved
Credential useObserved
Medium

Network access is mentioned

50 occurrences

A URL or network client appears in this source line. Review destinations, data sent, and trust boundaries; static text cannot establish actual network activity. This rule matched 50 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Note

File modification is described or implemented

176 occurrences

This line contains a possible file-write or redirection operation. Check destination paths and overwrite behavior; the static review did not write any file. This rule matched 176 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

High

Credential or secret material is referenced

8 occurrences

This line resembles a credential literal or reads a sensitive environment value. Do not expose its contents; verify whether it is a placeholder, required secret, or accidentally committed material. This rule matched 8 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

High

Dynamic command execution is referenced

A shell, dynamic evaluation, or process execution primitive appears here. Inspect arguments and input control. Presence in source does not prove a command ran. This rule matched 1 location(s) in the collected text; 1 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Editorial security note

Review the MCP server you connect and the token scopes you grant, since the skill can drive write operations against production data.

Where context can be spent

Discovery, activation, and resource layers have different meanings. Exact values appear only when the official token-counting method was run with a named model.

Exact token counts unavailable

All token values, including per-file inventory, are null until the pipeline performs an official exact count with an explicit model.

No token measurement was recorded with the required official method. This dossier does not substitute character counts, file sizes, or estimates.

Controlled evaluation

No controlled evaluation

This skill has only the evidence identified above. No task success, token efficiency, latency, or quality advantage is claimed.

Not tested

Use with the source in view

Install command
git clone https://github.com/Jeffallan/claude-skills.git cd claude-skills # Copy this skill directory into one of: # ~/.claude/skills/atlassian-mcp # .claude/skills/atlassian-mcp
  1. Open the pinned source at https://github.com/Jeffallan/claude-skills/blob/67c1961b180dc92cf08983344627109e983e8f51/skills/atlassian-mcp/SKILL.md.
  2. Review the license, prerequisites and all bundled reference files.
  3. Install the skill into a personal or project-level Claude Code skills directory.
  4. Restart or refresh Claude Code so the skill can be discovered.
Verify installation

Confirm atlassian-mcp/SKILL.md exists at the destination, then ask Claude Code to use the atlassian-mcp skill on a small test task.

Prerequisites

  • Needs a reachable Atlassian instance and valid credentials, which this review did not test.
  • Tool names differ between MCP servers, so the setup reference must be consulted.
  • Example server URLs and sample JQL are illustrative and may need adapting to your site.

Example prompts

Representative task

Use the atlassian-mcp skill to find unresolved bugs in project PROJ created in the last 7 days with JQL, probe the query with maxResults=1 first, and summarize them without modifying any ticket.

Inspect before use

Read the atlassian-mcp skill at https://github.com/Jeffallan/claude-skills/blob/67c1961b180dc92cf08983344627109e983e8f51/skills/atlassian-mcp/SKILL.md and its referenced files. Explain its workflow, required tools, permissions and the main risks before I decide whether to install it.

A decision, with its limits attached

Strengths

  • Builds safety into the workflow with read-only probes and confirmation before production writes.
  • Explicitly forbids hardcoded tokens and mixing authentication methods in one session.

Considerations

  • Adds an extra MCP server dependency and credential surface to your environment.
  • Relies on third-party servers such as the community mcp-atlassian package.
Research conclusion

A careful integration guide whose main value is its read-first safety posture around production Jira and Confluence data.

Traceable by construction

The dossier is a time-bound reading of a public artifact, not an endorsement. Use the source link to inspect the exact upstream material.

Jeffallanclaude-skillsskills/atlassian-mcp
Source type
Community
Commit
67c1961b180dc92cf08983344627109e983e8f51
Collected
20 Nov 2026
Last checked
20 Nov 2026
Upstream license
MIT
Repository stars
12,464
Content basis

Deterministic lexical parsing, YAML frontmatter validation, file inventory, source-described workflow extraction, and heuristic provisional classification of the supplied files only. Generated by machine; no LLM, execution, dynamic testing, or human editorial approval.