Connect your AI Agents to Lucidchart in minutes

What is a Lucidchart MCP?

It's an MCP server that connects your agents to Lucidchart through tools. Your agents can invoke these tools to create and retrieve diagrams, search documents across a workspace, manage folder contents, and control collaborator access, and more.

Lucid doesn't offer an MCP server purpose built for Lucidchart (they just have an MCP server for Lucid), but you can use one from a third-party platform, like Merge Agent Handler.

How can I use the Lucidchart MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

• Architecture diagram creation on new service launch: When a new service is merged into a GitHub repo, an agent creates a Lucidchart document in the appropriate workspace folder with the service name and key dependencies pre-populated, giving engineers a documentation starting point without manual setup

• Diagram retrieval during incidents: When an on-call engineer is paged, an agent searches Lucidchart for architecture diagrams matching the affected system and surfaces the most recent document directly in the incident Slack thread, cutting down the time spent hunting for context

• Collaborator access auditing: When a contractor or vendor is offboarded, an agent lists all Lucidchart documents they're a collaborator on, then removes their access and posts a summary to a security Slack channel for review

• Automated diagram export for design reviews: When a design review meeting is created in Google Calendar, an agent searches Lucidchart for the relevant diagram, exports it as a PDF, and posts the file to the meeting's Slack thread so reviewers have the latest version without opening Lucidchart

What are popular tools for Lucidchart's MCP server?

Here are some of the most commonly used tools:

• search_documents: searches across a Lucidchart workspace for documents matching a query string. Call this when an agent needs to locate a specific diagram before retrieving or exporting it

• get_document_contents: retrieves the full contents of a Lucidchart document by ID. Useful for agents that need to read diagram structure or metadata before taking a follow-on action

• create_document: creates a new Lucidchart document in a specified folder. Good for workflows that need to scaffold documentation automatically when a new project, service, or team is created

• export_document: exports a Lucidchart diagram to a shareable format such as PDF or PNG. Use this when an agent needs to attach a diagram to a ticket, email, or calendar event without requiring the recipient to have Lucidchart access

• list_document_user_collaborators: returns all users with access to a specific document. Helpful when an agent needs to audit who can view or edit a sensitive architecture diagram

• list_folder_contents: lists all documents and subfolders within a given folder. Call this when an agent needs to inventory a workspace section before searching, reorganizing, or reporting on its contents

What makes Merge Agent Handler's Lucidchart MCP server better than alternative Lucidchart MCP servers?

A few things make Merge Agent Handler's Lucidchart MCP server the stronger choice over building or using an alternative:

• Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Lucidchart, this means you can prevent proprietary architecture diagrams, internal system names, or confidential org charts from being surfaced to an agent that doesn't need that level of access

• Managed authentication and credentials: Merge stores and refreshes your Lucidchart OAuth credentials on your behalf. You never expose access tokens to an agent directly or deal with expired credentials breaking a workflow

• Real-time observability and audit trail: Every Lucidchart tool call is logged with the timestamp, tool name, inputs, and response metadata. You can see exactly which documents an agent accessed, exported, or modified without adding any custom logging

• Tool Packs and controlled access: Tool Packs let you bundle specific Lucidchart tools with tools from other connectors into a single scoped MCP endpoint. A read-only diagram retrieval agent never gets access to trash_document or collaborator management tools.

How can I start using Merge Agent Handler's Lucidchart MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account.

2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.

3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.

4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Lucidchart and complete the OAuth flow. Merge stores and manages the credentials going forward.

5.. Open a Claude Code session and start querying Lucidchart data directly. The first time you use a Lucidchart tool, a Magic Link may appear to complete connector authentication.

If you want to connect Merge Agent Handler's Lucidchart MCP with internal or customer-facing agentic products, you can follow the steps in our docs.

Can employees use Merge Agent Handler to connect their AI tools to Lucidchart?

Yes, Agent Handler for Employees lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Lucidchart without bypassing IT governance.

Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Agent Handler and gets individual credentials tied to their identity.

IT also provisions access by role or group via SCIM. A software engineer, for example, gets Lucidchart access to create and retrieve architecture diagrams, Confluence to link diagrams to technical docs, and Slack to share updates during incident response; while a business analyst gets Lucidchart access to document process flows, Jira to connect diagrams to project tickets, and Google Drive to export diagrams for stakeholder reviews.

Every tool call an employee's AI makes to Lucidchart is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.