Official Vendor Server
Atlassian✦ Lab Verified
Confluence
Search, read, and manage Confluence pages and spaces. Access team documentation and knowledge bases.
8.9/10
Score
814ms
Latency
100%
Uptime
23
Tools
OAuth
Auth
Ecosystem
Atlassian MCP Servers
2 specialized servers, 121 tools tested independently. Each link leads to a full review with tool-level evidence.
Quick Verdict
Use this for Jira and Confluence automation in current tests. Avoid it for latency-sensitive operations. Best area: jira operations with 39 tested tools. Biggest failure: you'll hit 19889ms max response times that could timeout workflows.
Lab Review
What We Found
What works: Jira operations run clean across 39 tools covering everything from issue creation to sprint management. The server handles both read and write operations consistently, with jira_batch_create_issues and jira_add_issues_to_sprint performing reliably in current tests. Confluence search and page operations complement this with stable content retrieval. Where it breaks: Nothing broke during testing, but latency spikes to nearly 20 seconds on some operations. We hit these delays across both Jira and Confluence tools without a clear pattern - bulk operations didn't consistently take longer than single-item calls. The median 814ms is manageable, but you'll see occasional multi-second waits that could timeout in stricter environments. What this means for your workflow: You can build reliably on both Jira issue management and Confluence content operations. Set generous timeouts - 30 seconds minimum - to handle the occasional slow response. The 100% success rate across 60 tools means core functionality is stable, but plan for variable response times in user-facing applications. For teams needing consistent sub-second responses, this latency variability is a blocker. For background automation and reporting tools, it delivers.
Reliability
Partial runtime test — 0 of 23 tools executed Score based on transport stability and schema completeness.
Score Breakdown
Reliability
0 of 0 executed tools succeeded.
Security
Score based on schema analysis and dependency audit.
Setup
Remote server with OAuth authentication.
Docs
23 tools with descriptions and input schemas.
Compatibility
Standard MCP protocol. Transport: OAuth.
Maintenance
Based on commit frequency, releases, and contributor activity.
Tools
23 available tools
Search Confluence content using simple terms or CQL. Args: ctx: The FastMCP context. query: Search query - can be simple text or a CQL query string. limit: Maximum number of results (1-50
Get content of a specific Confluence page by its ID, or by its title and space key. Args: ctx: The FastMCP context. page_id: Confluence page ID. If provided, 'title' and 'space_key' are ignor
Get child pages and folders of a specific Confluence page. Args: ctx: The FastMCP context. parent_id: The ID of the parent page. expand: Fields to expand. limit: Maximum number of chi
Get comments for a specific Confluence page. Args: ctx: The FastMCP context. page_id: Confluence page ID. Returns: JSON string representing a list of comment objects.
Get labels for Confluence content (pages, blog posts, or attachments). Args: ctx: The FastMCP context. page_id: Confluence content ID (page or attachment). Returns: JSON string represent
Show all 23 tools →Show less ↑
Add label to Confluence content (pages, blog posts, or attachments). Useful for: - Categorizing attachments (e.g., 'screenshot', 'diagram', 'legal-doc') - Tracking status (e.g., 'approved', 'needs-re
Create a new Confluence page. Args: ctx: The FastMCP context. space_key: The key of the space. title: The title of the page. content: The content of the page (format depends on conten
Update an existing Confluence page. Args: ctx: The FastMCP context. page_id: The ID of the page to update. title: The new title of the page. content: The new content of the page (form
Delete an existing Confluence page. Args: ctx: The FastMCP context. page_id: The ID of the page to delete. Returns: JSON string indicating success or failure. Raises: ValueError: If
Move a Confluence page to a new parent or space. Args: ctx: The FastMCP context. page_id: The ID of the page to move. target_parent_id: Target parent page ID. target_space_key: Target
Add a comment to a Confluence page. Args: ctx: The FastMCP context. page_id: The ID of the page to add a comment to. body: The comment content in Markdown format. Returns: JSON strin
Reply to an existing comment thread on a Confluence page. Args: ctx: The FastMCP context. comment_id: The ID of the parent comment to reply to. body: The reply content in Markdown format.
Search Confluence users using CQL (Cloud) or group member API (Server/DC). Args: ctx: The FastMCP context. query: Search query - a CQL query string for user search. limit: Maximum number
Get a historical version of a specific Confluence page. Args: ctx: The FastMCP context. page_id: Confluence page ID. version: The version number to retrieve. convert_to_markdown: Conv
Get a unified diff between two versions of a Confluence page. Args: ctx: The FastMCP context. page_id: Confluence page ID. from_version: Source version number. to_version: Target vers
Get view statistics for a Confluence page. Note: This tool is only available for Confluence Cloud. Server/Data Center instances do not support the Analytics API. Args: ctx: The FastMCP context.
Upload an attachment to Confluence content (page or blog post). If the attachment already exists (same filename), a new version is created. This is useful for: - Attaching documents, images, or files
Upload multiple attachments to Confluence content in a single operation. More efficient than calling upload_attachment multiple times. If files with the same names exist, new versions are created aut
List all attachments for a Confluence content item (page or blog post). Returns metadata about attachments including: - Attachment ID, title, and file type - File size and download URL - Creation/mod
Download an attachment from Confluence as an embedded resource. Returns the attachment content as a base64-encoded embedded resource so that it is available over the MCP protocol without requiring fi
Download all attachments for a Confluence content item as embedded resources. Returns attachment contents as base64-encoded embedded resources so that they are available over the MCP protocol without
Permanently delete an attachment from Confluence. **Warning**: This action cannot be undone! The attachment and ALL its versions will be permanently deleted. Use this tool to: - Remove outdated or i
Get all images attached to a Confluence page as inline image content. Filters attachments to images only (PNG, JPEG, GIF, WebP, SVG, BMP) and returns them as base64-encoded ImageContent that clients
FAQ
Frequently asked questions about Confluence
What latency should I expect for different types of operations?+
Development information operations show the highest latency, with jira_get_issue_development_info taking 19,889ms and jira_get_issues_development_info requiring 7,665ms. Most read operations complete in 500-1500ms range. Write operations like jira_create_issue and confluence_create_page typically take 1500-3000ms. Basic metadata operations like jira_get_issue_watchers and confluence_get_labels execute in under 400ms.
Which operations require the longest processing time?+
Three operations consistently exceeded 3 seconds: jira_get_issue_development_info at 19,889ms, jira_get_issues_development_info at 7,665ms, and jira_link_to_epic at 3,038ms. The development information endpoints particularly show extreme latency compared to standard JIRA operations. For time-sensitive applications, these specific operations may require timeout adjustments or asynchronous handling patterns.
What authentication scopes are required for write operations?+
Our testing used jira:read, jira:write, confluence:read, and confluence:write scopes. All 60 executed operations completed successfully with this scope configuration. Write operations like jira_create_issue, confluence_create_page, jira_update_issue, and confluence_update_page all functioned with the jira:write and confluence:write scopes respectively. No scope-related authentication failures occurred during testing.
How does batch processing perform compared to single operations?+
Batch operations show mixed performance characteristics. jira_batch_create_issues took 2,928ms compared to single jira_create_issue at 2,303ms, indicating overhead for batch processing. However, jira_batch_create_versions completed in 547ms versus single jira_create_version at 564ms. confluence_upload_attachments completed in just 3ms, showing significant efficiency gains over individual uploads for certain operations.
What happens when tools fail to execute?+
During our testing, all 60 executed tools completed successfully with no failures recorded. However, 12 tools were skipped due to write-dangerous classifications, meaning they perform destructive operations that could affect production data. These non-executed tools were not executed due to policy, dependency, or test-environment limitations rather than technical failures.
Which operations provide the fastest response times?+
Six operations completed in under 400ms: jira_get_issue_watchers (349ms), confluence_get_labels (350ms), confluence_get_attachments (294ms), confluence_download_content_attachments (311ms), confluence_get_page_images (303ms), and jira_get_sprint_issues (382ms). confluence_upload_attachments achieved 3ms, likely due to sandbox optimization. These represent the most responsive operations for real-time applications.
How do Confluence operations compare to JIRA in terms of performance?+
Confluence operations generally show more consistent latency patterns than JIRA. Most Confluence tools completed between 300-1400ms, while JIRA operations ranged from 349ms to 19,889ms. Confluence write operations like confluence_create_page (1,737ms) and confluence_update_page (2,213ms) performed similarly to JIRA write operations. However, JIRA development information endpoints introduced significant outliers in the performance profile.
Related
Explore more
Community