# How to integrate Confluence MCP with CrewAI

```json
{
  "title": "How to integrate Confluence MCP with CrewAI",
  "toolkit": "Confluence",
  "toolkit_slug": "confluence",
  "framework": "CrewAI",
  "framework_slug": "crew-ai",
  "url": "https://composio.dev/toolkits/confluence/framework/crew-ai",
  "markdown_url": "https://composio.dev/toolkits/confluence/framework/crew-ai.md",
  "updated_at": "2026-05-12T10:07:19.794Z"
}
```

## Introduction

This guide walks you through connecting Confluence to CrewAI using the Composio tool router. By the end, you'll have a working Confluence agent that can create a project documentation page in marketing space, add 'urgent' label to q3 planning page, publish team meeting summary as a blog post through natural language commands.
This guide will help you understand how to give your CrewAI agent real control over a Confluence account through Composio's Confluence MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Confluence with

- [ChatGPT](https://composio.dev/toolkits/confluence/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/confluence/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/confluence/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/confluence/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/confluence/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/confluence/framework/codex)
- [Cursor](https://composio.dev/toolkits/confluence/framework/cursor)
- [VS Code](https://composio.dev/toolkits/confluence/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/confluence/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/confluence/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/confluence/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/confluence/framework/cli)
- [Google ADK](https://composio.dev/toolkits/confluence/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/confluence/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/confluence/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/confluence/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/confluence/framework/llama-index)

## TL;DR

Here's what you'll learn:
- Get a Composio API key and configure your Confluence connection
- Set up CrewAI with an MCP enabled agent
- Create a Tool Router session or standalone MCP server for Confluence
- Build a conversational loop where your agent can execute Confluence operations

## What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.
Key features include:
- Agent Roles: Define specialized agents with specific goals and backstories
- Task Management: Create tasks with clear descriptions and expected outputs
- Crew Orchestration: Combine agents and tasks into collaborative workflows
- MCP Integration: Connect to external tools through Model Context Protocol

## What is the Confluence MCP server, and what's possible with it?

The Confluence MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Confluence account. It provides structured and secure access to your Confluence spaces, pages, and content, so your agent can perform actions like creating pages, publishing blog posts, organizing spaces, and managing metadata on your behalf.
- Automated page and space creation: Instantly create new Confluence pages or entire spaces, empowering your agent to generate project documentation, wikis, or knowledge bases as needed.
- Effortless blog post publishing: Let your agent draft and publish new blog posts within specified Confluence spaces to keep your team up-to-date and share knowledge seamlessly.
- Content labeling and metadata management: Have your agent add labels and custom properties to pages, blog posts, or spaces, making it easy to organize, tag, and categorize information for better discoverability.
- Private space setup and management: Direct your agent to create private, isolated workspaces for sensitive projects or teams, ensuring only authorized collaborators have access.
- Custom content property automation: Empower your agent to attach or update custom metadata on pages, blog posts, spaces, or whiteboards, streamlining your internal documentation workflows.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `CONFLUENCE_ADD_CONTENT_LABEL` | Add Content Label | Tool to add labels to a piece of content. Use after obtaining the content ID to tag pages or blog posts with metadata labels. |
| `CONFLUENCE_CQL_SEARCH` | CQL Search | Searches for content in Confluence using Confluence Query Language (CQL). CQL is a powerful query language that allows you to search across all Confluence content with advanced filtering capabilities including: - Full-text search: `text ~ "search term"` - searches within page content - Title search: `title ~ "meeting notes"` - searches page titles - Label filtering: `label = "important"` - filters by labels - Space filtering: `space = DEV` - limits search to specific spaces - Type filtering: `type = page` or `type = blogpost` - filters by content type - Creator filtering: `creator = currentUser()` - filters by content creator - Date filtering: `lastModified > now("-7d")` - filters by modification date - Combined queries: `text ~ "api" AND space = DOCS AND type = page` This action uses the Confluence REST API v1 search endpoint which fully supports CQL. |
| `CONFLUENCE_CREATE_BLOGPOST` | Create Blogpost | Tool to create a new Confluence blog post. Use when you need to publish content in a specific space. Response includes `data.id` for the post ID and `data._links.base` + `data._links.webui` for the URL. |
| `CONFLUENCE_CREATE_BLOGPOST_PROPERTY` | Create Blogpost Property | Tool to create a property on a specified blog post. Use when you need to add custom metadata to a blog post. Creates a new property with a key-value pair on a specified Confluence blog post. This allows users to add custom metadata relevant to the blog post. |
| `CONFLUENCE_CREATE_CONTENT_PROPERTY_FOR_WHITEBOARD` | Create Whiteboard Property | Tool to create a new content property on a whiteboard. Use when you need to attach custom metadata to a Confluence whiteboard. |
| `CONFLUENCE_CREATE_FOOTER_COMMENT` | Create Footer Comment | Tool to create a footer comment on a Confluence page, blog post, attachment, or custom content. Use when you need to add a comment without editing the page body itself. |
| `CONFLUENCE_CREATE_PAGE` | Create Page | Tool to create a new Confluence page in a specified space. Use when you need to create new documentation or content. |
| `CONFLUENCE_CREATE_PAGE_PROPERTY` | Create Page Property | Tool to create a property on a Confluence page. Use when you need to add custom metadata or settings to a page. |
| `CONFLUENCE_CREATE_PRIVATE_SPACE` | Create Private Space | Tool to create a private Confluence space. Use when you need an isolated workspace viewable only by its creator. |
| `CONFLUENCE_CREATE_SPACE` | Create Space | Tool to create a new Confluence space. Use when setting up a new knowledge area for organization. Must include a `plain.representation` field, e.g., `{"plain": {"representation": "plain", "value": "text here"}}`. Omitting this field causes a 400 error. |
| `CONFLUENCE_CREATE_SPACE_PROPERTY` | Create Space Property | Tool to create a new property on a Confluence space. Use after confirming the space ID when adding custom metadata. |
| `CONFLUENCE_CREATE_WHITEBOARD` | Create Whiteboard | Tool to create a new Confluence whiteboard. Use when you need to start a collaborative whiteboard session. |
| `CONFLUENCE_DELETE_BLOGPOST_PROPERTY` | Delete Blogpost Property | Tool to delete a blog post property. Use when you need to remove custom metadata from a specified blog post. |
| `CONFLUENCE_DELETE_CONTENT_PROPERTY_FOR_PAGE_BY_ID` | Delete Page Content Property | Tool to delete a content property from a page by property ID. Use when you need to remove custom metadata from a page for cleanup or auditing. This action deletes a specified content property from a Confluence page using its page ID and property ID. It is useful for removing outdated or unnecessary metadata. |
| `CONFLUENCE_DELETE_CONTENT_PROPERTY_FOR_WHITEBOARD_BY_ID` | Delete Whiteboard Content Property | Tool to delete a content property from a whiteboard by property ID. Use when you need to remove custom metadata from a whiteboard. |
| `CONFLUENCE_DELETE_PAGE` | Delete Page | Tool to delete a Confluence page. Use with caution as this permanently removes the page and its content with no recovery option. In move or migration workflows, confirm all target pages were successfully created before deleting source pages — partial creation failures combined with deletion result in unrecoverable data loss. |
| `CONFLUENCE_DELETE_SPACE` | Delete Space | Tool to delete a Confluence space by its key. Use when you need to permanently remove a space. |
| `CONFLUENCE_DELETE_SPACE_PROPERTY` | Delete Space Property | Tool to delete a space property. Use when you need to remove a property from a Confluence space after review. |
| `CONFLUENCE_DOWNLOAD_ATTACHMENT` | Download Attachment | Downloads an attachment from a Confluence page and returns a publicly accessible S3 URL. Use this when you need to share the attachment with users who don't have Confluence access. First use get_attachments to list attachments and get the attachment ID. |
| `CONFLUENCE_GET_ATTACHMENT_LABELS` | Get Attachment Labels | Tool to list labels on an attachment. Use after confirming the attachment ID to fetch its labels. |
| `CONFLUENCE_GET_ATTACHMENTS` | Get Attachments | Tool to retrieve attachments of a Confluence page. Use after confirming page ID to list its attachments (supports pagination). |
| `CONFLUENCE_GET_AUDIT_LOGS` | Get Audit Logs | Tool to retrieve Confluence audit records. Use when you need to fetch and filter audit logs for compliance or troubleshooting. |
| `CONFLUENCE_GET_BLOGPOST_BY_ID` | Get Blogpost by ID | Tool to retrieve a specific Confluence blog post by its ID. Use when you have a blog post ID and need detailed metadata and content. |
| `CONFLUENCE_GET_BLOGPOST_LABELS` | Get Blogpost Labels | Tool to retrieve labels of a specific Confluence blog post by ID. Use after obtaining the blog post ID to list its labels. |
| `CONFLUENCE_GET_BLOGPOST_LIKE_COUNT` | Get Blogpost Like Count | Tool to get like count for a Confluence blog post. Use after confirming the blog post ID to retrieve total likes. |
| `CONFLUENCE_GET_BLOGPOST_OPERATIONS` | Get Blogpost Operations | Tool to retrieve permitted operations for a Confluence blog post. Use after confirming the blog post ID to see allowed actions. |
| `CONFLUENCE_GET_BLOG_POSTS` | Get Blog Posts | Tool to retrieve a list of blog posts. Use when you need a paginated list of Confluence blog posts. |
| `CONFLUENCE_GET_BLOG_POSTS_FOR_LABEL` | Get Blog Posts For Label | Tool to list all blog posts under a specific label. Use when you have a label ID and need to retrieve associated blog posts. |
| `CONFLUENCE_GET_BLOGPOST_VERSION_DETAILS` | Get Blogpost Version Details | Tool to retrieve details for a specific version of a blog post. Use when you have a blogpostId and versionNumber and need detailed metadata for that version. |
| `CONFLUENCE_GET_BLOGPOST_VERSIONS` | Get Blogpost Versions | Tool to retrieve all versions of a specific blog post. Use when you have a blogpostId and need to list version numbers. |
| `CONFLUENCE_GET_CHILD_PAGES` | Get Child Pages | Tool to list all direct child pages of a given Confluence page. Use when you have a parent page ID and need to discover its direct descendants. Response nests child page data under `data.data.results`; unwrap this before iterating. Paginate using `_links.next` cursor until no further results to avoid missing children. |
| `CONFLUENCE_GET_CONTENT_PROPERTIES_FOR_BLOG_POST` | Get Blog Post Content Properties | Tool to retrieve all content properties on a blog post. Use when you need to list metadata properties set on a specific Confluence blog post. |
| `CONFLUENCE_GET_CONTENT_PROPERTIES_FOR_PAGE` | Get Page Content Properties | Tool to retrieve all content properties on a page. Use when you need to list metadata properties set on a specific Confluence page. |
| `CONFLUENCE_GET_CONTENT_RESTRICTIONS` | Get Content Restrictions | Tool to retrieve restrictions on a Confluence content item. Use when you need to see who can view or edit a page or blog post. |
| `CONFLUENCE_GET_CURRENT_USER` | Get Current User | Tool to get information about the currently authenticated user — always scoped to the account tied to the configured connection, not arbitrary users. Use CONFLUENCE_SEARCH_USERS to look up other users. Response contains nested metadata; key fields include accountId, displayName, and email for use in downstream logic. |
| `CONFLUENCE_GET_INLINE_COMMENTS_FOR_BLOG_POST` | Get Inline Comments for Blog Post | Tool to retrieve inline comments for a Confluence blog post. Use when you need inline comment details by blog post ID. |
| `CONFLUENCE_GET_LABELS` | Get Labels | Tool to retrieve all labels in a Confluence site; use for label discovery when you need to list or page through labels. For label-based filtering, use CONFLUENCE_GET_LABELS_FOR_PAGE or CONFLUENCE_GET_LABELS_FOR_SPACE_CONTENT instead. |
| `CONFLUENCE_GET_LABELS_FOR_PAGE` | Get Page Labels | Tool to retrieve labels of a specific Confluence page by ID. Labels are returned in `data.results[*].name` and are not available in CONFLUENCE_GET_PAGES responses. Use after obtaining the page ID to list its labels. Paginate using `start` and `limit` to avoid missing labels when count exceeds 25. |
| `CONFLUENCE_GET_LABELS_FOR_SPACE` | Get Labels for Space | Tool to list labels on a space. Use when you need to retrieve labels for a specific space. |
| `CONFLUENCE_GET_LABELS_FOR_SPACE_CONTENT` | Get Labels for Space Content | Tool to list labels on all content in a space. Use when you need to retrieve or filter content labels by space, with pagination and optional prefix filtering. For label discovery across a space before per-page filtering, use this tool first, then CONFLUENCE_GET_LABELS_FOR_PAGE; CONFLUENCE_SEARCH_CONTENT does not filter by labels. |
| `CONFLUENCE_GET_PAGE_ANCESTORS` | Get Page Ancestors | Tool to retrieve all ancestors for a given Confluence page by its ID. Use when you need the full page hierarchy. |
| `CONFLUENCE_GET_PAGE_BY_ID` | Get Page by ID | Tool to retrieve a Confluence page by its ID. Use when you have a page ID and need its detailed metadata and content. Response body is in `body.storage.value` as Confluence storage format (HTML); strip tags before plain-text use. Before calling CONFLUENCE_UPDATE_PAGE, fetch the latest version here — that tool requires `version.number` = current + 1, else a 409 conflict occurs. |
| `CONFLUENCE_GET_PAGE_FOOTER_COMMENTS` | Get Page Footer Comments | Tool to retrieve footer (non-inline) comments for a Confluence page. Use when you need to collect review feedback left as standard page comments. |
| `CONFLUENCE_GET_PAGE_INLINE_COMMENTS` | Get Page Inline Comments | Tool to retrieve inline comments for a Confluence page. Use when you need inline comment details by page ID. |
| `CONFLUENCE_GET_PAGE_LIKE_COUNT` | Get Page Like Count | Tool to get like count for a Confluence page. Use after confirming the page ID to retrieve total likes. |
| `CONFLUENCE_GET_PAGES` | Get Pages | Tool to retrieve a paginated list of Confluence pages. Results are permission-scoped to the authenticated user; empty results may reflect access restrictions. Omitting filters like spaceId or status can return unexpectedly broad result sets. Labels are not included in results; use CONFLUENCE_GET_LABELS_FOR_PAGE for label data. Timestamps are ISO 8601 UTC strings. |
| `CONFLUENCE_GET_PAGE_VERSIONS` | Get Page Versions | Tool to retrieve all versions of a specific Confluence page. Use to audit edit history or to get the latest version.number before calling CONFLUENCE_UPDATE_PAGE — using a stale version.number causes a 409 Conflict error. |
| `CONFLUENCE_CONFLUENCE_GET_SPACE_BY_ID` | Get Space by ID | Tool to retrieve a Confluence space by its ID. Use when you need detailed metadata of a specific space. Space names are non-unique; use the numeric spaceId or spaceKey from the response for stable identification in downstream operations such as CONFLUENCE_GET_SPACE_PROPERTIES, CONFLUENCE_GET_LABELS_FOR_SPACE, CONFLUENCE_GET_SPACE_CONTENTS, and CONFLUENCE_CREATE_BLOGPOST. |
| `CONFLUENCE_GET_SPACE_CONTENTS` | Get Space Contents | Tool to retrieve content in a Confluence space. Use when you need to list pages, blogposts, or attachments of a specific space key. Results are in data.results (not data.page.results). Paginate via start/limit (max 200/request); follow response._links.next until absent to avoid missing content. Only returns content accessible to the authenticated user — missing items may indicate permission restrictions. Atlassian Cloud enforces HTTP 429 rate limits; throttle to ~1–2 requests/second, honor Retry-After headers, and cap start ≤ 1000 for large spaces. Construct item URLs by combining data._links.base with each item's _links.webui. |
| `CONFLUENCE_GET_SPACE_PROPERTIES` | Get Space Properties | Tool to get properties of a Confluence space. Use when you need to retrieve custom metadata or settings stored as space properties. |
| `CONFLUENCE_GET_SPACES` | Get Spaces | Tool to retrieve a paginated list of Confluence spaces with optional filtering. Paginate by incrementing `start` in steps of `limit` until fewer results than `limit` are returned. Results are scoped to spaces visible to the authenticated user; absent spaces may be restricted rather than nonexistent. Use `spaceKey` or numeric space ID (not display name) for stable identification in downstream calls. Combined filters apply as AND logic — relax filters before concluding a space is missing. |
| `CONFLUENCE_GET_TASKS` | Get Tasks | Tool to list Confluence tasks (action items) with filtering by assignee, creator, space, page, blog post, status, and dates. Use when you need to retrieve user action items without unreliable keyword searching for "TODO". |
| `CONFLUENCE_GET_USER_ANONYMOUS` | Get Anonymous User | Tool to retrieve information about the anonymous user. Use when you need to obtain guest user details before unauthenticated interactions. |
| `CONFLUENCE_SEARCH_CONTENT` | Search Content | Searches for content by filtering pages from the Confluence v2 API with intelligent ranking. Since the native search endpoint is deprecated, this action: 1. Fetches pages from the v2 pages endpoint with pagination (up to 300 pages) 2. Applies intelligent client-side filtering with relevance scoring 3. Returns results ranked by match quality (exact phrase > all words > partial matches). NOTE: Only page titles are searched — queries matching only body content return no results. Results omit full body content and canonical URLs; use CONFLUENCE_GET_PAGE_BY_ID for complete page data. Cannot filter by author, date, or labels. Results reflect only pages accessible to the authenticated user. When multiple pages share similar titles, verify the correct page via spaceId or pageId before performing writes. |
| `CONFLUENCE_SEARCH_USERS` | Search Users | Searches for users using user-specific queries from the Confluence Query Language (CQL). |
| `CONFLUENCE_UPDATE_BLOGPOST` | Update Blogpost | Tool to update a Confluence blog post's title or content. Use when you need to modify an existing blog post. Ensure you have the latest version number before calling. |
| `CONFLUENCE_UPDATE_BLOGPOST_PROPERTY` | Update Blogpost Property | Tool to update a property of a specified blog post. Use when you need to modify custom metadata on a blog post. |
| `CONFLUENCE_UPDATE_CONTENT_PROPERTY_FOR_PAGE_BY_ID` | Update Page Content Property | Tool to update a content property on a Confluence page. Use when you need to modify an existing metadata property by its ID. |
| `CONFLUENCE_UPDATE_CONTENT_PROPERTY_FOR_WHITEBOARD_BY_ID` | Update Whiteboard Content Property | Tool to update a content property on a whiteboard. Use when you need to modify metadata on a Confluence whiteboard. |
| `CONFLUENCE_UPDATE_PAGE` | Update Page | Tool to update an existing Confluence page, replacing the entire page content. Use when you need to modify existing documentation or content. |
| `CONFLUENCE_UPDATE_SPACE_PROPERTY` | Update Space Property | Tool to update a space property. Use when you need to modify custom metadata stored on a Confluence space (requires fetching the current property version first). |
| `CONFLUENCE_UPDATE_TASK` | Update Task | Tool to update a Confluence task status. Use when you need to mark tasks as complete or incomplete in workflows or dashboards. |

## Supported Triggers

| Trigger slug | Name | Description |
|---|---|---|
| `CONFLUENCE_ATTACHMENT_ADDED_TRIGGER` | New Attachment Added | Triggers when a new attachment is uploaded to a Confluence page. Optionally filters by media type. |
| `CONFLUENCE_BLOG_POST_ADDED_TO_LABEL_TRIGGER` | Blog Post Added to Label | Triggers when a new blog post is added to a specific label in Confluence. |
| `CONFLUENCE_BLOGPOST_INLINE_COMMENT_ADDED_TRIGGER` | Blogpost Inline Comment Added | Triggers when a new inline comment is added to a Confluence blog post. |
| `CONFLUENCE_BLOGPOST_LIKE_COUNT_CHANGED_TRIGGER` | Blog Post Like Count Changed | Triggers when a Confluence blog post's like count changes (someone likes or unlikes). |
| `CONFLUENCE_BLOGPOST_UPDATED_TRIGGER` | Blog Post Updated | Triggers when a Confluence blog post is updated (any edit that creates a new version). |
| `CONFLUENCE_CONTENT_RESTRICTIONS_CHANGED_TRIGGER` | Content Restrictions Changed | Triggers when view or edit restrictions change on a Confluence page or blog post. Detects user/group restrictions being added, removed, or modified. |
| `CONFLUENCE_FOOTER_COMMENT_ADDED_TRIGGER` | New Footer Comment Added to Page | Triggers when a new footer comment is added to a Confluence page. |
| `CONFLUENCE_NEW_AUDIT_LOG_TRIGGER` | New Audit Log Record | Triggers when a new audit log record is created in Confluence. Requires Confluence Standard/Premium/Enterprise plan and 'Confluence Administrator' permission. |
| `CONFLUENCE_NEW_BLOG_POST_CREATED_TRIGGER` | New Blog Post Created | Triggers when a new blog post is created in Confluence. Optionally filters by space or status. |
| `CONFLUENCE_NEW_CHILD_PAGE_TRIGGER` | New Child Page Created | Triggers when a new child page is created under a specific parent page in Confluence. |
| `CONFLUENCE_NEW_CQL_CONTENT_MATCH_TRIGGER` | New CQL Content Match | Triggers when new Confluence content appears that matches a user-provided CQL query. |
| `CONFLUENCE_NEW_TASK_CREATED_TRIGGER` | New Task Created | Triggers when a new task (action item) is created in Confluence. |
| `CONFLUENCE_PAGE_CONTENT_PROPERTIES_CHANGED_TRIGGER` | Page Content Properties Changed | Triggers when content properties on a Confluence page are added, removed, or updated. |
| `CONFLUENCE_PAGE_CREATED_TRIGGER` | New Page Created | Triggers when a new page is created in Confluence. Optionally filters by space or status. |
| `CONFLUENCE_PAGE_INLINE_COMMENT_ADDED_TRIGGER` | New Inline Comment Added to Page | Triggers when a new inline comment is added to a Confluence page. |
| `CONFLUENCE_PAGE_LIKE_COUNT_CHANGED_TRIGGER` | Page Like Count Changed | Triggers when a Confluence page's like count changes (someone likes or unlikes). |
| `CONFLUENCE_PAGE_MOVED_TRIGGER` | Page Moved | Triggers when a Confluence page is moved to a different location in the page hierarchy. |
| `CONFLUENCE_PAGE_UPDATED_TRIGGER` | Page Updated | Triggers when a Confluence page is updated (any edit that creates a new version). |
| `CONFLUENCE_PAGE_VERSION_CREATED_TRIGGER` | Page Version Created | Triggers when a new version is created for a specific Confluence page. |
| `CONFLUENCE_SPACE_CONTENT_ADDED_TRIGGER` | New Space Content Added | Triggers when new content (pages or blog posts) is added to a Confluence space. Attachments are not supported at space level; use the 'New Attachment Added' trigger instead. |
| `CONFLUENCE_SPACE_CREATED_TRIGGER` | New Space Created | Triggers when a new Confluence space is created. Optionally filters by space type or status. |
| `CONFLUENCE_SPACE_DETAILS_CHANGED_TRIGGER` | Space Details Changed | Triggers when a Confluence space's details change (name, description, status, owner, icon, etc.). |
| `CONFLUENCE_SPACE_PROPERTIES_CHANGED_TRIGGER` | Space Properties Changed | Triggers when properties on a Confluence space are added, removed, or updated. |

## Creating MCP Server - Stand-alone vs Composio SDK

The Confluence MCP server is an implementation of the Model Context Protocol that connects your AI agent to Confluence. It provides structured and secure access so your agent can perform Confluence operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before starting, make sure you have:
- Python 3.9 or higher
- A Composio account and API key
- A Confluence connection authorized in Composio
- An OpenAI API key for the CrewAI LLM
- Basic familiarity with Python

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) and create an API key. You'll need credits to use the models, or you can connect to another model provider.
- Keep the API key safe.
Composio API Key
- Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

**What's happening:**
- composio connects your agent to Confluence via MCP
- crewai provides Agent, Task, Crew, and LLM primitives
- crewai-tools[mcp] includes MCP helpers
- python-dotenv loads environment variables from .env
```bash
pip install composio crewai crewai-tools[mcp] python-dotenv
```

### 3. Set up environment variables

Create a .env file in your project root.
What's happening:
- COMPOSIO_API_KEY authenticates with Composio
- USER_ID scopes the session to your account
- OPENAI_API_KEY lets CrewAI use your chosen OpenAI model
```bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here
```

### 4. Import dependencies

**What's happening:**
- CrewAI classes define agents and tasks, and run the workflow
- MCPServerHTTP connects the agent to an MCP endpoint
- Composio will give you a short lived Confluence MCP URL
```python
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")
```

### 5. Create a Composio Tool Router session for Confluence

**What's happening:**
- You create a Confluence only session through Composio
- Composio returns an MCP HTTP URL that exposes Confluence tools
```python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["confluence"])

url = session.mcp.url
```

### 6. Initialize the MCP Server

**What's Happening:**
- Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
- MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
- Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
- Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
- Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.
```python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
```

### 7. Create a CLI Chatloop and define the Crew

**What's Happening:**
- Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
- Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
- Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
- Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
- Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
- Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.
```python
print("Chat started! Type 'exit' or 'quit' to end.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[agent], tasks=[task], verbose=False)
    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
```

## Complete Code

```python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["confluence"],
)
url = session.mcp.url

# Configure LLM
llm = LLM(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY"),
)

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")
```

## Conclusion

You now have a CrewAI agent connected to Confluence through Composio's Tool Router. The agent can perform Confluence operations through natural language commands.
Next steps:
- Add role-specific instructions to customize agent behavior
- Plug in more toolkits for multi-app workflows
- Chain tasks for complex multi-step operations

## How to build Confluence MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/confluence/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/confluence/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/confluence/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/confluence/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/confluence/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/confluence/framework/codex)
- [Cursor](https://composio.dev/toolkits/confluence/framework/cursor)
- [VS Code](https://composio.dev/toolkits/confluence/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/confluence/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/confluence/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/confluence/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/confluence/framework/cli)
- [Google ADK](https://composio.dev/toolkits/confluence/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/confluence/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/confluence/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/confluence/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/confluence/framework/llama-index)

## Related Toolkits

- [Gmail](https://composio.dev/toolkits/gmail) - Gmail is Google's email service with powerful spam protection, search, and G Suite integration. It keeps your inbox organized and makes communication fast and reliable.
- [Outlook](https://composio.dev/toolkits/outlook) - Outlook is Microsoft's email and calendaring platform for unified communications and scheduling. It helps users stay organized with powerful email, contacts, and calendar management.
- [Slack](https://composio.dev/toolkits/slack) - Slack is a channel-based messaging platform for teams and organizations. It helps people collaborate in real time, share files, and connect all their tools in one place.
- [Gong](https://composio.dev/toolkits/gong) - Gong is a platform for video meetings, call recording, and team collaboration. It helps teams capture conversations, analyze calls, and turn insights into action.
- [Microsoft teams](https://composio.dev/toolkits/microsoft_teams) - Microsoft Teams is a collaboration platform that combines chat, meetings, and file sharing within Microsoft 365. It keeps distributed teams connected and productive through seamless virtual communication.
- [Slackbot](https://composio.dev/toolkits/slackbot) - Slackbot is a conversational automation tool for Slack that handles reminders, notifications, and automated responses. It boosts team productivity by streamlining onboarding, answering FAQs, and managing timely alerts—all right inside Slack.
- [2chat](https://composio.dev/toolkits/_2chat) - 2chat is an API platform for WhatsApp and multichannel text messaging. It streamlines chat automation, group management, and real-time messaging for developers.
- [Agent mail](https://composio.dev/toolkits/agent_mail) - Agent mail provides AI agents with dedicated email inboxes for sending, receiving, and managing emails. It empowers agents to communicate autonomously with people, services, and other agents—no human intervention needed.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Chatwork](https://composio.dev/toolkits/chatwork) - Chatwork is a team communication platform with group chats, file sharing, and task management. It helps businesses boost collaboration and streamline productivity.
- [Clickmeeting](https://composio.dev/toolkits/clickmeeting) - ClickMeeting is a cloud-based platform for running online meetings and webinars. It helps businesses and individuals host, manage, and engage virtual audiences with ease.
- [Dailybot](https://composio.dev/toolkits/dailybot) - DailyBot streamlines team collaboration with chat-based standups, reminders, and polls. It keeps work flowing smoothly in your favorite messaging platforms.
- [Dialmycalls](https://composio.dev/toolkits/dialmycalls) - Dialmycalls is a mass notification service for sending voice and text messages to contacts. It helps teams and organizations quickly broadcast urgent alerts and updates.
- [Dialpad](https://composio.dev/toolkits/dialpad) - Dialpad is a cloud-based business phone and contact center system for teams. It unifies voice, video, messaging, and meetings across your devices.
- [Discord](https://composio.dev/toolkits/discord) - Discord is a real-time messaging and VoIP platform for communities and teams. It lets users chat, share media, and collaborate across public and private channels.
- [Discordbot](https://composio.dev/toolkits/discordbot) - Discordbot is an automation tool for Discord servers that handles moderation, messaging, and user engagement. It helps communities run smoothly by automating routine and complex tasks.
- [Echtpost](https://composio.dev/toolkits/echtpost) - Echtpost is a secure digital communication platform for encrypted document and message exchange. It ensures confidential data stays private and protected during transmission.
- [Egnyte](https://composio.dev/toolkits/egnyte) - Egnyte is a cloud-based platform for secure file sharing, storage, and governance. It helps teams collaborate efficiently while maintaining data compliance and security.
- [Google Meet](https://composio.dev/toolkits/googlemeet) - Google Meet is a secure video conferencing platform for virtual meetings, chat, and screen sharing. It helps teams connect, collaborate, and communicate seamlessly from anywhere.
- [Heartbeat](https://composio.dev/toolkits/heartbeat) - Heartbeat is a plug-and-play platform for building and managing online communities. It helps you organize users, channels, events, and discussions in one place.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Confluence MCP?

With a standalone Confluence MCP server, the agents and LLMs can only access a fixed set of Confluence tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Confluence and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Confluence tools.

### Can I manage the permissions and scopes for Confluence while using Tool Router?

Yes, absolutely. You can configure which Confluence scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Confluence data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)