What MCP is

The Model Context Protocol (MCP) is an open standard that allows AI models and external applications to securely access real-time, contextual data from connected systems. In the context of Elium, MCP enables a bridge between your knowledge base and AI tools such as ChatGPT or other compliant assistants.

Through MCP, an AI assistant can query your Elium content, for example, to answer user questions, summarise documentation, or provide context-aware support without needing to manually copy or export data. Access is managed via OAuth authentication, ensuring that only authorised users and applications can retrieve information based on their Elium permissions.

Each Elium instance exposes its MCP endpoint at https://your-platform-name.elium.com/services/mcp, which can be used to connect your platform’s knowledge securely to external AI ecosystems.

Connect your assistant

Follow the guide for your assistant:

These assistants register or identify themselves when you connect them, so there is nothing to create in Elium. To connect another assistant, or to understand how Elium authorises a connection, see MCP authentication.

As a system administrator, you can see and manage every connected assistant from one place: see Manage MCP apps.

Available tools

Once a connection is established, the Elium MCP server offers tools to search, read, create and update articles. Every tool runs with the permissions of the authenticated user, so an assistant can only ever access content that user is already allowed to see in Elium.

Search and read

Tool	What it does
`findRelevantArticles`	Searches the whole knowledge base by meaning. The default way to answer a question.
`findSpecificArticles`	Searches with filters: keywords, template, spaces, date range.
`readArticle`	Returns the content and metadata of one article, including its language and version.
`readAsset`	Returns the plain text of a document attached to an article.
`findSpaces`	Lists the spaces the user can access.
`findTemplates`	Lists the article templates available.
`readTemplate`	Returns the fields of one template and the body its articles start from.
`findTagCategories`	Lists the tag categories, and which ones a space requires.
`findTags`	Finds tags by name, or lists the tags of a category.
`findUsers`	Finds users by name, email address or profile.

Each tool is described in Search and read content with MCP.

Create and update

Tool	What it does
`createArticle`	Creates an article from Markdown, with its template, fields, tags and attached files, when writing is enabled.
`updateArticle`	Changes the title, the body or the template fields of an article, attaches files and saves a draft when writing is enabled.
`createArticleTranslation`	Adds a language to a translated article, as a draft.
`tagArticle`	Adds or removes tags on an article, without creating a draft.
`findSections`	Lists the sections (folders) in a space.
`getContentSyntax`	Returns the Markdown specification used for article bodies.
`checkArticleBody`	Validates a Markdown body before creating an article.
`getUploadUrl`	Gives the assistant an address to upload a file to, so it can attach the file to an article.
`createTag`	Creates a tag in a tag category, or returns the tag of that name if it already exists.
`updateTag`	Renames a tag or moves it to another category. Administrators only.
`createTagCategory`	Creates a tag category. Administrators only.
`updateTagCategory`	Renames a tag category or changes who can add tags to it. Administrators only.

Create and update articles with MCP describes each tool and the steps to create or update an article.

Examples in practice

Here are a few things a connected assistant can do, and the tools it uses for each.

"How do I request parental leave?" A meaning-based search (findRelevantArticles) answers from the most relevant HR articles, with links.
"Summarise the policies we updated this quarter." A filter by template and date range (findSpecificArticles), then a read of each result (readArticle) to summarise it.
"Is our data-retention policy still up to date?" A read of the article (readArticle), then a check of its review date and approval status before answering.
"Which spaces can I post to?" A list of the user's spaces and their rights (findSpaces).
"Find every FAQ article in the Support space." A template lookup (findTemplates), a space lookup (findSpaces), then a filtered search (findSpecificArticles).
"Read the PDF attached to this article." After reading an article (readArticle), the assistant calls readAsset with the document UUID from the body to retrieve its full text.
"Create a guide in the Installation folder of the Handbook space." A space lookup (findSpaces), then a section lookup (findSections) to find the folder, then createArticle with the section ID.
"Write up this meeting with the Meeting template, tagged Finance." A template lookup (findTemplates), a read of its fields (readTemplate), a tag lookup (findTags), then createArticle with the template, the field values and the tag.
"Check if this Markdown is valid before creating the article." A dry run (checkArticleBody) reports any formatting issues before createArticle writes anything.
"Attach this PDF to the meeting notes." An upload address (getUploadUrl), the upload of the file by the assistant, then updateArticle with the file attached and placed in the body.
"Add a French version of the travel policy." A read of the article in English (readArticle), then createArticleTranslation with the French title and body, saved as a draft.

Every example runs with the user's own permissions. The assistant never sees content that the user could not already open in Elium.