Integration

Merge Knowledge Base integration

Merge Knowledge Base is Merge's unified API for wikis and help centers: one call shape reads whichever knowledge base (Confluence, Notion, Guru, Zendesk Guide, SharePoint and others) a Merge Linked Account connects. List and read articles with their title, status, visibility, hierarchy and a temporary download link for their content (the content is not returned inline), the containers (spaces, folders, categories) that hold them, attachments, users (names and email addresses) and groups, and the permissions on articles and containers. It is read-only. Not exposed: raw third-party data, passthrough requests and Linked Account, key, webhook, field mapping, scope and sync administration. Calls go to Merge's US region only (api.merge.dev): an organization on Merge's EU or APAC tenant cannot connect here. Authentication is a Merge API key (Authorization: Bearer) plus one Linked Account's account token (X-Account-Token), so one connection reads one knowledge base account.

Connect Merge Knowledge Base How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Merge Knowledge Base.Built from the 13 Merge Knowledge Base tools below, on the connection you add once.

What you can do with Merge Knowledge Base

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Article, 2 operations

get_articleGet articleGETReturns one article by Merge id: title, description, status, visibility, author, last editor, parent and root containers, permissions, attachment ids and a presigned, time-limited link to download its content (not returned inline).
list_articlesList articlesGETLists articles with title, description, status, visibility, author, parent and root containers, permissions and a presigned link to download each article's content, filterable by container, parent article, status and type. Paginated with cursor.

Attachment, 2 operations

get_attachmentGet attachmentGETReturns one attachment of an article or container by Merge id: name, description and URL.
list_attachmentsList attachmentsGETLists the attachments of articles and containers with their name, description and URL. Cursor-paginated.

Container, 2 operations

get_containerGet containerGETReturns one container (space, folder, collection, section, category or database) by Merge id: name, description, status, visibility, URL, parent article or container and permissions.
list_containersList containersGETLists the containers that hold articles (spaces, folders, collections, sections, categories, databases) with name, status, visibility, URL, parent and permissions. Filter by parent article, parent container or type.

Group, 2 operations

get_groupGet groupGETReturns one group of users by Merge id: name, parent group and member user ids (whole users, with names and email addresses, when expanded).
list_groupsList groupsGETLists the groups of users in the knowledge base with name, parent group and member user ids (whole users, with names and email addresses, when expanded). Cursor-paginated.

User, 2 operations

get_userGet userGETReturns one knowledge base user by Merge id: name and email address (personal data).
list_usersList usersGETLists the knowledge base's users with their name and email address (personal data). Cursor-paginated.

Account detail, 1 operation

get_account_detailsGet account detailsGETReturns the Linked Account behind the connection: integration name and slug, category, status, end user organization and email, and account type.

Available action, 1 operation

get_available_actionsGet available actionsGETReturns the integration behind the Linked Account and, per Common Model, the operations it supports (FETCH, CREATE...), the fields it fills and the parameters a create must send.

Sync status, 1 operation

get_sync_statusGet sync statusGETReturns the sync state of each Common Model for the Linked Account: last and next sync start, last result and finish time. Data read through the other tools is as fresh as the last sync.

Use Merge Knowledge Base from Claude Code, Cursor or Codex

Connect Merge Knowledge Base in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Merge Knowledge Base operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Merge Knowledge Base

Create your workspace
Sign up free. Nothing to install.
Connect Merge Knowledge Base once
Add your Merge Knowledge Base connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.