Confluence MCP Server
MCP ServerFreeSearch, read, and create Confluence wiki pages via MCP.
Capabilities14 decomposed
confluence full-text page search with jql-style filtering
Medium confidenceEnables semantic and keyword-based search across Confluence pages using the Confluence Search API with support for CQL (Confluence Query Language) filters. The implementation wraps the native Confluence search endpoint with parameter marshaling for space filtering, content type restrictions, and result pagination, returning structured page metadata including page IDs, titles, spaces, and excerpt snippets. Supports both Cloud and Server/Data Center deployments with automatic API format adaptation.
Abstracts Confluence Search API differences between Cloud and Server/Data Center deployments through automatic format adaptation, enabling single-codebase support for both deployment models while exposing CQL filtering capabilities that most MCP servers omit entirely.
Provides native CQL filtering support and multi-deployment compatibility that generic REST API wrappers lack, enabling more precise documentation retrieval than simple keyword search.
confluence page creation and hierarchical content authoring
Medium confidenceEnables AI agents to create new Confluence pages with full support for parent-child page hierarchies, content formatting (HTML/XHTML), and metadata assignment. The implementation uses the Confluence Content API with automatic body format detection (storage format for Server/Data Center, rich text format for Cloud), parent page resolution, and space assignment. Supports inline attachments, labels, and custom properties through the underlying Confluence API schema.
Implements automatic body format detection and conversion between Cloud (rich text) and Server/Data Center (storage format) deployments, allowing single tool invocations to work across both platforms without client-side format negotiation.
Handles hierarchical page creation with parent resolution in a single API call, whereas generic Confluence API clients require manual parent ID lookup and separate calls for page creation.
tool registration and discovery with dependency injection
Medium confidenceRegisters 72 Confluence and Jira tools with FastMCP framework using dependency injection pattern for client instantiation and configuration. The implementation uses FastMCP's tool decorator system to expose tools with automatic schema generation, parameter validation, and error handling. Supports tool access control through permission decorators and conditional tool availability based on deployment type or authentication method.
Uses FastMCP's decorator-based tool registration with dependency injection for client instantiation, enabling automatic schema generation and parameter validation without manual tool definition boilerplate.
Provides automatic tool schema generation and dependency injection, whereas manual MCP implementations require explicit schema definition and client instantiation logic.
jira issue creation and field management
Medium confidenceEnables creating Jira issues with full support for custom fields, issue types, projects, and field validation. The implementation uses the Jira Create Issue API with automatic field schema discovery, type coercion, and validation error reporting. Supports both Cloud and Server/Data Center with field name mapping and custom field ID resolution.
Implements automatic field schema discovery and type coercion with custom field ID resolution, enabling issue creation with custom fields without manual field ID lookup or type specification.
Provides field validation and custom field support in a single API call, whereas generic Jira API clients require manual field schema lookup and separate validation calls.
jira issue search and jql query execution
Medium confidenceEnables searching Jira issues using JQL (Jira Query Language) with support for complex filters, sorting, and result pagination. The implementation wraps the Jira Search API with JQL validation, result expansion (issue details, changelog, comments), and automatic pagination handling. Supports both Cloud and Server/Data Center with JQL dialect adaptation.
Implements JQL query execution with automatic result expansion and pagination handling, enabling single API calls to fetch complex issue sets with full metadata without manual pagination logic.
Provides JQL search with automatic result expansion and pagination, whereas generic Jira API clients expose raw search endpoints requiring manual pagination and expansion parameter management.
jira issue updates and workflow transitions
Medium confidenceEnables updating Jira issues (fields, status, assignee) and executing workflow transitions with automatic permission checking and field validation. The implementation uses the Jira Update Issue API with support for bulk field updates, transition execution with required field validation, and changelog tracking. Supports both Cloud and Server/Data Center with field name mapping.
Implements workflow transition execution with automatic required field validation, enabling single API calls to transition issues through workflow states without separate validation calls.
Provides workflow transition support with field validation, whereas generic Jira API clients expose raw update endpoints requiring manual transition lookup and field validation.
confluence page content reading with format normalization
Medium confidenceRetrieves full page content from Confluence with automatic format normalization across Cloud and Server/Data Center deployments. The implementation fetches pages via the Content API with expand parameters for body content, metadata, and version history, then normalizes storage format (Server/DC) or rich text format (Cloud) into a consistent representation. Includes support for retrieving page hierarchies, child pages, and version history metadata.
Implements automatic format normalization between Cloud (rich text) and Server/Data Center (storage format) deployments, exposing a unified content representation to clients regardless of backend platform, eliminating the need for format-specific parsing logic.
Provides transparent format conversion and version history retrieval in a single call, whereas direct Confluence API clients require manual format detection and separate API calls for version metadata.
confluence space and page hierarchy traversal
Medium confidenceEnables navigation and discovery of Confluence space structures, page hierarchies, and content organization through tools that list spaces, retrieve page trees, and resolve parent-child relationships. The implementation uses the Confluence Content API with recursive expansion parameters to fetch page hierarchies, space metadata, and permission information. Supports filtering by space type (global, personal) and pagination for large hierarchies.
Provides recursive page hierarchy expansion with automatic parent-child relationship resolution, allowing single API calls to fetch multi-level page trees rather than requiring separate calls per hierarchy level.
Exposes space and page hierarchy traversal as first-class operations, whereas generic Confluence API clients require manual recursive calls and client-side tree construction.
confluence page comments and discussion management
Medium confidenceEnables reading, creating, and managing comments on Confluence pages through tools that fetch comment threads, post new comments, and update existing comments. The implementation uses the Confluence Comments API with support for nested replies, mention resolution (@username), and comment metadata (author, timestamp, edit history). Supports both inline comments and page-level discussions.
Implements mention resolution and nested reply support through the Confluence Comments API, enabling AI agents to participate in page discussions with awareness of user mentions and reply threading.
Provides comment management as a first-class capability with mention support, whereas generic API wrappers expose raw comment endpoints without mention resolution or discussion threading.
confluence page labels and metadata tagging
Medium confidenceEnables adding, removing, and querying labels (tags) on Confluence pages for content organization and discovery. The implementation uses the Confluence Labels API to manage page labels, retrieve pages by label, and support label hierarchies (prefix-based organization like 'team:backend', 'status:draft'). Supports bulk label operations and label-based filtering in search queries.
Supports prefix-based label hierarchies (e.g., 'team:backend', 'status:draft') with convention-based organization, enabling semantic label structures without enforced schema validation.
Provides label management with hierarchical prefix support, whereas generic Confluence API clients expose only flat label operations without organizational conventions.
confluence page attachments and file management
Medium confidenceEnables uploading, downloading, and managing file attachments on Confluence pages through tools that handle file I/O, attachment metadata, and version tracking. The implementation uses the Confluence Attachments API with support for multipart file uploads, attachment versioning, and metadata (filename, size, MIME type, upload timestamp). Supports both Cloud and Server/Data Center with automatic format adaptation.
Implements multipart file upload with automatic MIME type detection and attachment versioning, enabling AI agents to upload generated files with full metadata tracking without manual format specification.
Provides attachment management with version tracking and metadata extraction, whereas generic file upload tools require manual MIME type specification and offer no version history.
multi-transport mcp server deployment (stdio, sse, http)
Medium confidenceExposes the Confluence and Jira tools through multiple transport protocols (stdio for IDE integration, Server-Sent Events for streaming, streamable-http for service deployments) using FastMCP framework. The implementation abstracts transport selection through CLI arguments and environment variables, with automatic server lifecycle management (startup, shutdown, error handling). Supports both synchronous and asynchronous tool execution with streaming response support.
Implements transport abstraction through FastMCP with automatic server lifecycle management, enabling single codebase deployment across stdio (IDE), SSE (streaming), and HTTP (service) transports without transport-specific code paths.
Provides multi-transport support with unified tool definitions, whereas custom MCP implementations typically require separate code paths for each transport protocol.
flexible authentication with oauth 2.0, api tokens, and pat support
Medium confidenceSupports multiple authentication methods (API tokens, Personal Access Tokens, OAuth 2.0 3LO) with automatic credential resolution from environment variables, CLI arguments, or per-request HTTP headers. The implementation uses a credential chain pattern that checks multiple sources in priority order (CLI args > environment variables > HTTP headers for multi-tenant deployments). Includes OAuth 2.0 3LO flow support for user-delegated access without storing credentials.
Implements credential chain pattern with per-request HTTP header support for multi-tenant deployments, enabling shared MCP server instances to serve multiple users with different Confluence/Jira credentials without credential leakage.
Provides multi-tenant authentication support with per-request credential override, whereas single-credential MCP servers require separate instances per user or shared credentials.
cloud and server/data center deployment abstraction
Medium confidenceAutomatically detects and adapts to Confluence/Jira deployment type (Cloud vs Server/Data Center) with format-specific API handling, response parsing, and feature availability checks. The implementation uses deployment detection logic that inspects instance URL patterns and API response formats, then routes requests through deployment-specific code paths for body format conversion (rich text vs storage format), field name mapping, and API endpoint differences.
Implements automatic deployment detection and format adaptation, routing requests through deployment-specific code paths without requiring explicit configuration or client-side logic for API differences.
Provides transparent Cloud/Server/DC compatibility with automatic format conversion, whereas generic Confluence API clients require manual deployment-specific configuration and format handling.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with Confluence MCP Server, ranked by overlap. Discovered automatically through the match graph.
PageWise AI
Instant Insight into Your Confluence...
mcp-azure-confluence
MCP server: mcp-azure-confluence
Jira MCP Server
Search, create, and manage Jira issues and sprints via MCP.
mcp-atlassian
MCP server for Atlassian tools (Confluence, Jira)
Danswer (Onyx)
Enterprise AI assistant across company docs.
Outline
AI-driven writing, collaboration, and document...
Best For
- ✓Teams building AI agents that need to retrieve Confluence documentation as context
- ✓Documentation-heavy organizations automating knowledge discovery workflows
- ✓Developers integrating Confluence as a knowledge base for RAG systems
- ✓AI-powered documentation generation systems that need to publish directly to Confluence
- ✓Teams automating knowledge base population from structured data or AI outputs
- ✓Developers building content management workflows that treat Confluence as a content sink
- ✓AI platforms integrating Confluence/Jira through MCP protocol
- ✓Teams building custom tool registries with dynamic tool availability
Known Limitations
- ⚠Search results limited to 50 items per request by default; requires pagination for larger result sets
- ⚠CQL filter syntax varies between Cloud and Server/Data Center; server-specific filters may not translate
- ⚠No full-text indexing optimization — relies on Confluence's native search performance which can be slow on large instances
- ⚠Content format differs between Cloud (rich text) and Server/Data Center (storage format); requires format-specific HTML/XHTML markup
- ⚠Parent page resolution requires exact page title or ID; no fuzzy matching for parent lookup
- ⚠No built-in conflict detection — concurrent page creation with identical titles may cause unexpected behavior
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
About
Community MCP server for Atlassian Confluence wiki platform. Enables searching pages, reading and creating content, managing spaces, and querying page hierarchies in Confluence workspaces.
Categories
Alternatives to Confluence MCP Server
Search the Supabase docs for up-to-date guidance and troubleshoot errors quickly. Manage organizations, projects, databases, and Edge Functions, including migrations, SQL, logs, advisors, keys, and type generation, in one flow. Create and manage development branches to iterate safely, confirm costs
Compare →AI-optimized web search and content extraction via Tavily MCP.
Compare →Scrape websites and extract structured data via Firecrawl MCP.
Compare →Are you the builder of Confluence MCP Server?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →