The MCP Atlassian Server integrates Confluence and Jira with Model Context Protocol (MCP) to provide direct access to content and issues.
Confluence Integration:
Search content using CQL (Confluence Query Language)
Access pages, attachments, and comments
Filter content by space and limit results
Jira Integration:
Search issues using JQL (Jira Query Language)
Retrieve issue details including status, assignee, and timestamps
Specify fields and limit results
Tools:
confluence_search: Perform CQL-based searches
jira_search: Execute JQL-based searches
Resource Templates:
Access Confluence pages using confluence://{space_key}/pages/{title}
Access Jira issues using jira://{project_key}/issues/{issue_key}
Integrates Atlassian products with the Model Context Protocol, enabling access to content across Atlassian's ecosystem.
Provides searching capabilities for Confluence content using CQL, with access to pages, attachments, comments, and space filtering.
Enables searching Jira issues via JQL, retrieving issue details including status, assignments, and timestamps.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Atlassian Server find open issues in the ENG project assigned to me"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server pro integraci Atlassian produktů (Confluence, Jira) s Model Context Protocol. Tento nástroj umožňuje snadný přístup k vašemu Confluence obsahu a Jira ticketům přímo přes MCP rozhraní.
Vyhledávání obsahu pomocí CQL (Confluence Query Language)
Přístup ke stránkám, přílohám a komentářům
Filtrování podle prostoru (space)
Vyhledávání issues pomocí JQL (Jira Query Language)
Získávání detailů o issues včetně statusu, přiřazení a časových značek
Related MCP server: Atlassian MCP Server
To install Atlassian Integration Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @petrsovadina/mcp-atlassian --client claudegit clone https://github.com/petrsovadina/mcp-atlassian.git
cd mcp-atlassian
npm install
npm run buildNastavte následující proměnné prostředí:
CONFLUENCE_URL=https://your-domain.atlassian.net/wiki
CONFLUENCE_USERNAME=your-email@domain.com
CONFLUENCE_API_TOKEN=your-api-tokenJIRA_URL=https://your-domain.atlassian.net
JIRA_USERNAME=your-email@domain.com
JIRA_API_TOKEN=your-api-tokenPřidejte následující konfiguraci do vašeho MCP settings souboru:
{
"mcpServers": {
"atlassian": {
"command": "node",
"args": ["/path/to/mcp-atlassian/build/index.js"],
"env": {
"CONFLUENCE_URL": "your-confluence-url",
"CONFLUENCE_USERNAME": "your-username",
"CONFLUENCE_API_TOKEN": "your-api-token",
"JIRA_URL": "your-jira-url",
"JIRA_USERNAME": "your-username",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}Vyhledávání v Confluence obsahu pomocí CQL.
{
"query": "type=page AND space='Engineering'", // CQL dotaz
"limit": 10 // volitelný limit výsledků (1-50)
}Vyhledávání Jira issues pomocí JQL.
{
"jql": "project = ENG AND status = Open", // JQL dotaz
"fields": "summary,status,assignee", // volitelné pole
"limit": 10 // volitelný limit výsledků (1-50)
}confluence://{space_key}/pages/{title}
jira://{project_key}/issues/{issue_key}
const result = await mcp.use('confluence_search', {
query: "type=page AND space='Engineering' ORDER BY created DESC",
limit: 5
});const result = await mcp.use('jira_search', {
jql: "project = ENG AND status = 'In Progress'",
fields: "summary,status,assignee,created",
limit: 5
});Pokud chcete přispět k vývoji, můžete:
Forkovat repozitář
Vytvořit feature branch
Commitnout vaše změny
Pushnout branch
Vytvořit Pull Request
MIT
Search Confluence content using CQL
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Results limit (1-50) | |
| query | Yes | CQL query string |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions 'CQL' (Confluence Query Language) but doesn't disclose behavioral traits like pagination, rate limits, error handling, or what happens with invalid queries. The description is minimal and lacks critical operational context for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste, making it appropriately sized and front-loaded. However, it's overly concise to the point of under-specification, lacking necessary details for effective use, which slightly reduces its score from perfect.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a search tool with potential complexity (CQL queries), the description is incomplete. It doesn't explain return values, error cases, or behavioral nuances, leaving significant gaps for an AI agent to understand how to invoke and interpret results effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with clear documentation for 'query' (CQL query string) and 'limit' (results limit 1-50). The description adds no additional parameter semantics beyond what the schema provides, such as CQL syntax examples or default behaviors. Baseline 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Search Confluence content using CQL' clearly states the action (search) and resource (Confluence content), but it's vague about what 'content' specifically includes (pages, blogs, spaces, etc.) and doesn't distinguish from sibling tool 'jira_search'. It provides a basic purpose but lacks specificity about scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description doesn't mention the sibling 'jira_search' tool or any other search methods, nor does it specify prerequisites like authentication or appropriate contexts for CQL queries. Usage is implied through the name but not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Jira issues using JQL
| Name | Required | Description | Default |
|---|---|---|---|
| fields | No | Comma-separated fields | |
| jql | Yes | JQL query string | |
| limit | No | Results limit (1-50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states the basic function but doesn't describe important behavioral aspects like authentication requirements, rate limits, pagination behavior (beyond the 'limit' parameter), error handling, or what format/search capabilities JQL provides. For a search tool with no annotation coverage, this leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a search tool and front-loads the essential information. Every word earns its place by specifying what, where, and how.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete for a search tool with 3 parameters. It doesn't explain what the search returns (issue objects, summaries, or full details), how results are structured, or any behavioral constraints. For a tool that presumably returns complex Jira issue data, more context about output format would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description mentions JQL but doesn't add any parameter-specific context beyond what's in the schema. The baseline of 3 is appropriate when the schema does the heavy lifting, though the description could have explained JQL syntax or field selection patterns.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Search Jira issues using JQL' clearly states the action (search), resource (Jira issues), and method (JQL). It distinguishes from the sibling tool 'confluence_search' by specifying Jira issues rather than Confluence content. However, it doesn't specify what kind of search results are returned or the scope beyond 'issues'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling 'confluence_search' tool or any other Jira tools that might exist. There's no indication of prerequisites, limitations, or typical use cases beyond the basic function.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0confluence_searchjira_searchScored across 2 tools
The two tools are clearly distinct: one searches Confluence content using CQL, and the other searches Jira issues using JQL. There is no overlap in purpose or target resource, making misselection highly unlikely.
Both tools follow a consistent naming pattern: [product]_[action] (confluence_search, jira_search). This verb_noun style is uniform and predictable across the set.
With only two tools, the server feels thin for covering Atlassian's ecosystem. While Confluence and Jira are major products, the lack of additional operations (e.g., create, update, delete) or coverage of other Atlassian tools (e.g., Bitbucket, Trello) makes the scope appear incomplete.
The server only provides search functionality for two Atlassian products, missing essential CRUD operations (e.g., create pages in Confluence, update issues in Jira) and other lifecycle actions. This creates significant gaps that will limit agent workflows and likely cause failures in broader tasks.
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
Share one project context across ChatGPT, Claude, Telegram and any MCP client.
Cross-tool persistent memory and context for AI assistants over MCP.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
