--- type: Documentation title: Connect AI assistants (MCP) description: Connect Claude, ChatGPT, Microsoft 365 Copilot, and other AI assistants to your Librario library via the Model Context Protocol — one OAuth sign-in, the same permissions you have in the web UI. resource: https://www.librario.de/en/docs/integration/mcp tags: - docs - integration --- # Connect AI assistants (MCP) > **Plan option:** > > Available in plans with **MCP access**. [Compare plans→](/en/preise) Let Claude and ChatGPT search your Librario library directly — no more dragging PDFs into a chat window or copying search results by hand. Librario provides a server for the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) — an open standard for connecting AI applications to external systems. Your AI assistant is the client, Librario is the server. Once you've connected it, it can on your behalf: - **Search in natural language**: _"Find publications about EN 1993-1-1 steel column buckling published since 2020."_ - **Look up publication details**: _"Tell me more about publication #42."_ - **Download, read, or process attached files** — through a short-lived signed link, or directly in the conversation on AI tools that support reading MCP resources. ## Quickstart You need two things: 1. **Your personal MCP URL from Librario.** Click your avatar in the top right and open **Integrations**. The page shows whether your plan includes MCP and provides your tenant-specific MCP URL — copy it from the MCP card. You'll paste this URL into your AI tool in a moment. 2. **An AI-assistant account on a plan that supports custom connectors** (per-vendor requirements below). > **Which AI tools work?:** > > Librario works with any AI tool that supports the [Model Context Protocol](https://modelcontextprotocol.io/) and an OAuth sign-in. Claude.ai, Claude Desktop, and ChatGPT are the most common examples and are walked through below. For any other MCP-capable tool, follow its own instructions for adding a custom MCP connector and use your Librario MCP URL there. ### Claude.ai (web — recommended) 1. In Claude.ai, open **Connectors** settings (under **Customize** on personal plans, **Settings** on Team / Enterprise plans) — directly at . 2. Click \*\*+ Add custom connector\*\* and paste your MCP URL. Leave authentication on \*\*OAuth\*\*. 3. Claude.ai opens a new tab to the Librario sign-in page. Sign in. The consent screen then shows the requested permissions. 4. Review the permissions and the per-tool checkboxes, then click \*\*Authorize\*\*. 5. Try a search query: \> \_Find publications about steel column buckling since 2020.\_ Requirement: a Claude.ai \*\*Pro\*\*, \*\*Team\*\*, or \*\*Enterprise\*\* plan — custom connectors are not available on the free plan. ### Claude Desktop (macOS & Windows) 1. Install [Claude Desktop](https://claude.ai/download) and sign in. 2. Open \*\*Settings → Connectors → Add custom connector\*\* (or in a chat window click \*\*+\*\* → \*\*Connectors\*\*). 3. Paste your MCP URL. Leave authentication on \*\*OAuth\*\*. Click \*\*Add\*\*. 4. Claude Desktop opens your browser to the Librario sign-in. Sign in, review the permissions, and click \*\*Authorize\*\*. 5. Try a search query. ### ChatGPT 1. Click your profile picture → \*\*Settings → Connectors → Advanced\*\* and toggle \*\*Developer mode\*\* on. 2. Back at \*\*Connectors\*\*, click \*\*+ Add custom connector\*\*. 3. Paste your Librario MCP URL, leave authentication on \*\*OAuth\*\*, and confirm \*\*I trust this application\*\*. 4. ChatGPT opens a new tab to the Librario sign-in. Sign in, review the permissions, and click \*\*Authorize\*\*. 5. Try a search query. Requirement: a paid ChatGPT plan (Plus, Pro, Business, Team, Enterprise, or Edu) — the free tier does not support custom connectors. On \*\*Business, Team, Enterprise, and Edu workspaces\*\* the workspace administrator must first enable Developer mode and grant you access before the steps above will work. On the consent screen you can untick individual tools — for example, disable file downloads, or disable letting the AI read file content directly while still allowing download links, while keeping search and details enabled. By default all tools are checked. Your selection is remembered per connection; an unticked tool returns a permission error to the assistant on the next call. ## Connect Microsoft 365 Copilot With Claude and ChatGPT, each person sets up their own connection. Microsoft 365 Copilot works differently: someone with administrator rights registers Librario centrally once, and the connection is then available to everyone who is licensed for it. Microsoft's Copilot landscape is tangled — the products have been renamed several times, and there are two unrelated ways to connect an MCP server like Librario: - \*\*[Federated connector](https://learn.microsoft.com/en-us/microsoft-365/copilot/connectors/federated-connectors-overview)\*\* — an administrator registers the Librario MCP URL once in the Microsoft 365 admin center. Librario then appears for every licensed person in Microsoft 365 Copilot Chat and the Researcher agent. Each person needs a \*\*Microsoft 365 Copilot license\*\*. Access is read-only (search, detail lookup, file download) — no write actions. - \*\*Copilot Studio agent\*\* — if your organisation builds its own agents, you can add Librario as an MCP tool inside a Copilot Studio agent instead. This is more flexible but needs a separate Copilot Studio license and is aimed at people who develop agents. For most organisations the federated connector is the right path — it is described below. The Copilot Studio route is sketched at the end. ### Set up the federated connector (admin) 1. You need the \*\*Global Administrator\*\* or \*\*AI Administrator\*\* role in Microsoft Entra. 2. Set up authentication first. Librario registers AI tools via \*\*OAuth\*\*; register an OAuth connection in the Teams Developer Portal and note the registration ID. 3. In the \*\*Microsoft 365 admin center\*\*, open \*\*Copilot → Connectors\*\*, choose \*\*Create a new connector → Connect to MCP server\*\*, and enter a display name, your Librario MCP URL, and the registration ID. 4. Release the connector — optionally via a \*\*staged rollout\*\* to selected groups first, then to everyone. Microsoft changes the menus of this still-young area frequently. For the current, click-by-click instructions, see Microsoft's documentation: [Set up custom federated connectors](https://learn.microsoft.com/en-us/microsoft-365/copilot/connectors/set-up-custom-federated-connectors). ### Use the federated connector (end user) Once an administrator has released the connector, Librario appears as a source in the \*\*Researcher agent\*\* and in the research mode of Microsoft 365 Copilot Chat. On first use, Copilot signs you in to Librario — the same OAuth sign-in and consent screen as for Claude and ChatGPT. After that you search in natural language, for example: \_"Find publications about steel column buckling since 2020."\_ > **What to keep in mind:** > > As of May 2026, federated connectors are generally available but were only rolled out recently — labels and menu paths in the admin center may still change. Access is read-only and available only in certain Copilot surfaces (Copilot Chat, Researcher, Copilot in Excel). Every person using it needs a paid Microsoft 365 Copilot license. ### Alternative: Copilot Studio agent Organisations that build their own agents can instead add Librario directly to a Copilot Studio agent as an MCP tool — via \*\*Tools → Add a tool → New tool → Model Context Protocol\*\*. This route requires a Copilot Studio license. Details: [Connect your agent to an existing MCP server](https://learn.microsoft.com/en-us/microsoft-copilot-studio/mcp-add-existing-server-to-agent). ## Connect Google Gemini With Google the answer comes in two parts, and the most important limitation goes first: \*\*the everyday Gemini app at [gemini.google.com](https://gemini.google.com/), and Gemini in Gmail and Docs, cannot connect a third-party MCP server.\*\* That surface offers only a curated catalogue of Google and partner extensions, with no setting to enter the Librario MCP URL. Don't go looking for one there. Two paths do work: - \*\*[Gemini Enterprise](https://docs.cloud.google.com/gemini/enterprise/docs)\*\* — a separate, separately-licensed Google Cloud product (not the same as "Gemini for Workspace"). Here an administrator registers Librario as a "custom MCP server data store". This capability is currently in \*\*Preview\*\*. - \*\*Gemini CLI\*\* — Google's open command-line tool. It lets an individual connect Librario without any admin involvement. ### Set up Gemini Enterprise (admin) Setup happens in the \*\*Google Cloud console\*\*, not the Google Workspace Admin console. 1. Lift the organisation policy that blocks custom MCP server data stores by default, and grant the \*\*Discovery Engine Editor\*\* IAM role. 2. Register Gemini Enterprise as an OAuth client and note the client ID and client secret. 3. Under \*\*Data Stores → Create data store → Custom MCP Server\*\*, create an entry with your Librario MCP URL, the OAuth endpoints (authorization and token URL), client ID, client secret, and scopes. 4. Complete the OAuth sign-in, then explicitly enable the tools you want — none are enabled by default. For the current, click-by-click instructions, see Google's documentation: [Set up your custom MCP server data store](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/custom-mcp-server/set-up-custom-mcp-server). Once the data store is set up, Librario is available to users as a source in Gemini Enterprise. They search in natural language, and the agent calls the enabled Librario tools when needed — signing in to Librario via OAuth on their behalf on first use. ### Use Gemini CLI (developer) If you work with the [Gemini CLI](https://geminicli.com/), add the Librario MCP URL as an MCP server in the CLI configuration. The Librario tools are then available to the model in every CLI session. This path needs no admin setup. > **What to keep in mind:** > > As of May 2026, Gemini Enterprise’s custom MCP server feature is in **Preview** — its scope, menus, and labels may still change. Gemini Enterprise is a separate product, licensed separately from Google Workspace: the Gemini embedded in Gmail, Docs, and at gemini.google.com does not currently support connecting external MCP servers — the setup described here works only in Gemini Enterprise. ## Manage and revoke connections The \*\*Integrations\*\* page lists every connected AI assistant — one row per connection with name, connect time, last-used timestamp, and the granted permissions. Click \*\*Revoke\*\* on a row to end that connection immediately. The assistant's next request to Librario returns `HTTP 401`; refreshing expired tokens also fails. The only way to regain access is a new authorisation. > **MCP is disabled?:** > > If the MCP card says the connection was disabled by your administrator, someone with the [administrator role](/en/docs/administration/rollen#administratorin) has switched MCP off for the entire account. Existing connections are preserved and resume without reconnecting once it is re-enabled. Administrators control this in the [account settings](/en/docs/administration/kontoeinstellungen#mcp_disabled).