Connect your AI Agents to Confluence in minutes

How can I use the Confluence MCP server?

Here are some use cases worth implementing:

• Incident response coordination: When an incident occurs, your agent can pull runbooks and troubleshooting guides from Confluence while simultaneously creating incident tickets in Jira and posting status updates to Slack
  

• Code review context enrichment: Your agent can fetch design documents and technical specifications from Confluence when reviewing pull requests in GitHub. For instance, when a developer submits a PR, it can automatically retrieve the related docs from Confluence and add them as context in the PR comments
  

• Sales enablement from product knowledge: Your agent can pull product documentation, competitive positioning, and feature descriptions from Confluence to assist sales teams in Salesforce or Slack
  

• Support ticket enrichment: Your agent can search Confluence for known issues, troubleshooting guides, and solution articles while processing support tickets in apps like Zendesk or Intercom
  

• Sprint planning with documentation context: Your agent can retrieve product requirements, technical constraints, and past retrospective notes from Confluence while helping teams plan sprints in Jira or Linear

What are popular tools for Confluence’s MCP server?

Here are some popular tools across data types:

Blog posts

• <code class="blog_inline-code">get_blogposts</code>
• <code class="blog_inline-code">get_blogpost</code>
• <code class="blog_inline-code">create_blogpost</code>
• <code class="blog_inline-code">update_blogpost</code>

Pages

• <code class="blog_inline-code">search_pages</code>
• <code class="blog_inline-code">get_pages</code>
• <code class="blog_inline-code">create_page</code>
• <code class="blog_inline-code">get_page_inline_comments</code>

Spaces

• <code class="blog_inline-code">create_space</code>
• <code class="blog_inline-code">get_space</code>
• <code class="blog_inline-code">get_space_content</code>
• <code class="blog_inline-code">list_all_spaces</code>

What makes Merge Agent Handler’s Confluence MCP server better than alternative Confluence MCP servers?

When using Confluence through Merge Agent Handler, developers benefit from platform-level capabilities that apply across all connectors:

• Enterprise-grade security and DLP: All tool inputs and outputs are scanned by a configurable security gateway that can block, redact, or mask sensitive data before it reaches Confluence or your agent. Rules can be applied globally, per connector, per Tool Pack, or by region, with real-time alerts when violations occur

• Authentication and credential management: Merge Agent Handler manages user onboarding, OAuth flows, credential storage, and token refresh so agents never manage secrets directly. Agent Handler also supports both individual and shared authentication models, automatically manages token rotation, and validates credentials

• Real-time observability and audit trails: Every tool call is logged with full context, including the user, tool and arguments used, response data, status codes, and timestamps. Server logs are fully-searchable by user, Tool Pack, connector, date, and rule violations, making it easy to drill down into specific incidents for debugging and compliance auditing

• Evaluation before production: Tools can be validated in the Evaluation Suite to ensure correct behavior and expected outcomes before deployment. You can set up structured test prompts, validate that agents call the correct tools with appropriate parameters, simulate failure cases like expired tokens, and test across different scenarios

Can I set security rules for Confluence tool calls in Merge Agent Handler?

Yes, you can set a wide range of security rules for Confluence tool calls in Merge Agent Handler.

For example, you can:

• Block internal project codenames in searches. Prevent your agents from searching Confluence spaces for confidential project codenames or internal code words that should remain restricted

• Redact employee IDs before creating pages. Automatically strip employee identification numbers before your agents create or update Confluence pages or comments
  

• Log when agents access restricted spaces. Track and audit whenever your agents read from or search within specific Confluence spaces designated as confidential or executive-only
  

• Block customer PII in page updates. Prevent your agents from adding customer names, phone numbers, or addresses to Confluence documentation or wiki pages
  

• Redact database connection strings. Automatically remove database credentials, server addresses, or connection strings before they're written to Confluence technical documentation

How can I start using Merge Agent Handler’s Confluence MCP server?

Here's how to get started with Merge Agent Handler's Confluence MCP server:

1. Create your Agent Handler account. Go to Merge Agent Handler's sign up page to register for free and access the platform dashboard.

2. Configure a Tool Pack. Tool Packs define which connectors and tools your agent can use. From the Tool Packs section, click Create Tool Pack, include Confluence as a connector, and choose between Individual or Shared authentication depending on your requirements.

3. Register a User identity. Navigate to Registered Users and create an entry; this represents the identity (either human or system) that will perform actions through your agent. Agent Handler handles Confluence authentication automatically with a guided flow, so you don't need to build custom OAuth logic.

4. Test in the Sandbox environment. Before going live, verify that everything works as expected. Access your Tool Pack's Sandbox and experiment with Confluence tool calls like searching spaces, retrieving pages, or updating documentation.

5. Integrate with your agent application. Connect your agent to Agent Handler through one of these approaches:

• Model Context Protocol: Copy the MCP server configuration from your Tool Pack settings and add it to your agent's MCP client setup. This grants your agent immediate access to all Confluence tools through the protocol

• Direct API integration: Use Agent Handler's REST API to list available tools and invoke them programmatically. You'll need your API key, Tool Pack ID, and Registered User ID for requests