# Confluence MCP connector Connect Confluence to Elaichi and Claude, ChatGPT, Cursor, or any MCP client can search, read, create, and update Confluence pages, spaces, and attachments inside each person's own access, with every action logged. Source: https://elaichi.ai/connectors/confluence/ ## Facts | | | | --- | --- | | Application | Confluence | | Category | Knowledge Management | | AI tools | 18 | | Authentication | Connects over OAuth | | Needs your own OAuth app | No | | MCP endpoint | https://api.elaichi.ai/mcp | | Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent | | Tools advertised by name | Yes | ## What you can ask once Confluence is connected - Summarize pages updated in the Engineering space this week. - Which Confluence spaces have no pages created this month? - Draft a release notes page in the Product space. ## Connect Confluence in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Confluence. 2. Optionally set Share with, then press Connect. 3. Approve it in Confluence. Confluence's own window opens. Whoever approves it decides what this connection can reach. Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Confluence tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Connect Confluence to Claude Endpoint: https://api.elaichi.ai/mcp 1. Open Customize, then Connectors. 2. Press Add. 3. Name it, paste the MCP server URL, then Continue. 4. Sign in and approve. On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves. ## Connect Confluence to ChatGPT Endpoint: https://api.elaichi.ai/mcp 1. Open Plugins, then press the + button. 2. Name it and paste the endpoint into Server URL. 3. Leave Authentication on OAuth, then tick the risk acknowledgement. 4. Press Create, then sign in and approve. Works on the web today. The plugin directory lives at chatgpt.com/plugins. ## Connect Confluence to Cursor Endpoint: https://api.elaichi.ai/mcp 1. Open `~/.cursor/mcp.json`. 2. Add the endpoint under `mcpServers`. 3. Reload Cursor, then sign in and approve. Set up per machine, so repeat it on each computer you work from. ## Connect Confluence to any MCP client Endpoint: https://api.elaichi.ai/mcp 1. Add the endpoint as a remote MCP server. 2. Sign in and approve. The Elaichi Agent already has these tools, with nothing to set up. ## What the consent screen decides Only Read is granted by default, which is not enough to call a Confluence tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone. ## What teams do with Confluence through Elaichi ### Find the answer before the customer waits Support. Ask for the runbook or troubleshooting page that covers a customer's problem and get the relevant section back, without opening five spaces to find it. ### Draft the spec page after the meeting Product. Turn meeting notes into a new page in the right Confluence space, with the standard headings and labels the team already uses. ### Keep the runbook current after an incident Engineering. Update the on-call page with what actually happened and what changed, so the next engineer reads the fix and not last quarter's version. ### Answer policy questions from the handbook HR. Ask what the parental leave or expense policy says and get the answer with a link to the page it came from, instead of forwarding the question to HR. ### Review who has access to which spaces IT. List Confluence users and groups, see who belongs where, and remove someone from a group when their role changes. ### Pull together what several pages say Operations. Search across spaces for everything written about a vendor, process, or project and get a short summary with the pages it drew from. ## Frequently asked questions ### How do I connect Confluence to Claude? Two steps. In Elaichi, choose Confluence and sign in with your Atlassian account, which connects over OAuth, so there is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude will ask you to sign in to Elaichi, and from then on it can work with your Confluence pages and spaces. ### Does Confluence work with ChatGPT and Cursor as well as Claude? Yes. Once Confluence is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Confluence once and every client you use gets it. ### What can an AI agent actually do with my Confluence data? With Confluence connected, an agent can search across your spaces, read pages and their attachments, create new pages, and update existing ones. It can also list spaces, labels, users, and groups, remove someone from a group, and read the Confluence audit log. It cannot delete pages or spaces through this connector. ### Does connecting Confluence give the AI access to every space? No. An agent only sees the Confluence spaces and pages the signed-in person can already open, because every call runs as that person, and Confluence's own space permissions and page restrictions still apply. Elaichi can narrow that further, for example to reading only, but it can never widen what someone is allowed to see in Confluence. ### Can my team share one Confluence connection? Yes. One person connects Confluence in Elaichi and shares the connection with a team, and nobody else handles a credential or signs in to Atlassian. Each teammate still signs in to Elaichi as themselves, so every page created or updated in Confluence is logged under the person who did it. ### Can I stop an agent from changing pages or groups in Confluence? Yes. In Elaichi you restrict each Confluence action separately, so you can allow searching and reading while blocking page updates, page creation, or removing members from groups. A blocked action is never shown to Claude, ChatGPT, or any other client, so no prompt can trigger it. ### What happens to a Confluence connection when someone leaves? When you offboard a person in Elaichi, their access to Confluence through every AI client ends at once. If they had shared a Confluence connection with a team, it keeps working for everyone else. If you want to remove Confluence entirely, disconnecting it once in Elaichi removes it from every client at the same time. ## All 18 Confluence tools Every tool below is callable through https://api.elaichi.ai/mcp once Confluence is connected, subject to the toolbox it is in and the restrictions on the caller. - **List all Confluence users** (List). Search users using the CQL query in Confluence. Returns user details including accountId, username, displayName, email, profilePicture, and personalSpace. Note some fields may be null due to privacy settings. - **Get single Confluence user by ID** (Get). Get user information by accountId in Confluence. Returns displayName, accountId, profilePicture, isGuest status, operations allowed, personalSpace details, and business and personal contact details. - **List all Confluence accessible resources** (List). Get list of accessible resources in Confluence. Returns id, name, url, scopes, and avatarUrl for each resource. - **List all Confluence groups** (List). Get all user groups in Confluence. Returns groups ordered alphabetically by name with fields id, name, and type. - **Get single Confluence group by ID** (Get). Get group information by id in Confluence. Returns type, name, id, and _links fields of the group. - **Confluence groups remove member** (Delete). Remove user as a member from a group in Confluence using groupId and accountId. Returns no content on success. - **List all Confluence audit logs** (List). Get audit records filtered by startDate and endDate in Confluence. Returns fields including author, remoteAddress, creationDate, summary, description, category, sysAdmin, superAdmin, affectedObject, changedValues, and associatedObjects. - **List all Confluence pages** (List). Get all pages in Confluence filtered by id, space_id, status, or title. Returns fields including id, status, title, spaceId, parentId, version details, and body content in specified format. - **Get single Confluence page by ID** (Get). Get a specific page by id in Confluence. Returns fields including id, status, title, spaceId, parentId, version details, body content, labels, properties, operations, likes, versions, and isFavoritedByCurrentUser. - **Create a Confluence page** (Create). Create a page in Confluence with required spaceId and title if status is current. Returns id, status, title, spaceId, parentId, authorId, createdAt, version details, body content, labels, properties, operations, likes, versions, and favorite status. - **Update a Confluence page by ID** (Update). Update a page by id in Confluence. Requires id, status, title, body, and version number. Returns updated page fields including id, status, title, spaceId, parentId, version details, body content, labels, properties, operations, likes, versions, and links. Note: Changing status from 'current' to 'draft' deletes existing draft; restoring 'trashed' pages changes status only. - **List all Confluence spaces** (List). Retrieves a list of spaces from your Confluence account. A space is a collection of related pages, blogs, and other content that helps teams organize work. You can filter the results by space ids, keys, type (e.g., global, personal), status (e.g., current, archived), labels, favorited-by, and not-favorited-by query parmeters. You can also control the response format for space description by using the description-format query parameter. Use the include-icon query parameter to include a space icon in the response. The response consists of each space’s key, name, type, status, description, the ID of the author who created the space, creation timestamp, and description. - **Get single Confluence space by ID** (Get). Get space by id in Confluence. Returns fields id, key, name, type, status, authorId, createdAt, homepageId, description, icon, labels, properties, operations, permissions, and _links. - **List all Confluence search** (List). Get search results for content using the cql query in Confluence. Returns results array with content id, type, title, space, version, body views, and excerpt fields. Note user-specific CQL fields are deprecated. - **List all Confluence user groups** (List). Get group memberships for user with accountId in Confluence. Returns groups with fields type, name, and id. - **List all Confluence me** (List). Use this endpoint to get the information about the currently authenticated user in the Confluence account. - **List all Confluence attachments** (List). Get attachments for page with id in Confluence. Returns fields id, status, title, createdAt, mediaType, fileSize, webuiLink, downloadLink, and version details. Results limited by limit parameter. - **List all Confluence labels** (List). Get all labels in Confluence. Returns label id, name, and prefix fields. Use limit to control number of labels returned.