The Lucid Model Context Protocol (MCP) server acts as a digital bridge, connecting your Lucid documents to AI tools such as ChatGPT, Claude, and Microsoft Copilot. With the Lucid MCP server enabled, you can use natural language to search, retrieve, edit, and summarize your Lucid documents, as well as create diagrams, enhancing your AI-driven workflow.
Plan availability: Free, Individual, Team, and Enterprise.
- Not available on FedRAMP accounts.
- Read the Lucid Plans article for more information about what is available on your account.
Set up the Lucid MCP server
The Lucid MCP server is compatible with any MCP client, including those listed below. While the setup process varies depending on the client you use, the server URL required to set up the Lucid MCP is the same:
- https://mcp.lucid.app/mcp
- This URL is not intended to be visited in your browser. It is a parameter you will use to connect the AI tool to Lucid’s MCP server.
The Lucid MCP server can connect to any MCP client. Steps to connect to Lucid’s MCP server may vary between AI tools. Refer to the documentation provided by the following compatible AI tools linked below:
- ChatGPT
- Claude desktop
- Claude web
- Microsoft Copilot Studio
- Github Copilot
- Cursor
- Claude Code
- Windsurf
This is not an exhaustive list of supported clients—the Lucid MCP server can connect to any MCP client.
Note: Consult each AI tool's documentation for specific requirements. AI tools you set up with the Lucid MCP server are Non-Lucid Applications (as defined in our Terms of Service). Your use of these AI tools is subject to the agreement between you and the third-party provider, including applicable licensing requirements, plan limitations, and version compatibility.
We work hard to ensure the information in the Lucid Help Center is up-to-date. However, the third-party resources linked in this section are not owned by Lucid and may change without notice. If you notice that this information is outdated, please let us know here.
MCP connectors
Lucid offers a quick and seamless connection to Lucid’s MCP server with the connectors for ChatGPT and Claude. For steps to set up these connectors, check out these articles:
Additional MCP server options
Lucid offers different MCP server configurations depending on your security needs and desire for early access to new features. When configuring your AI tool, you can choose the server option that best fits your workflow.
- Lucid repositories MCP server: Connect to this server to only reference content in Process Accelerator Repositories.
- Lucid read-only MCP server: Provide AI tools with search and view-only permissions for your Lucid data
JSON config requirements
Some AI tools may require you to manually edit a JSON config file to connect them to an MCP server.
If your AI tool supports the HTTP transport method, use this JSON config:
"Lucid Software": {
"type": "http",
"url": "https://mcp.lucid.app/mcp"
}
If your AI tool does not support the HTTP transport method, you need to run a local server to forward HTTP requests to Lucid’s MCP server. This can be accomplished using the mcp-remote Node.js package. Make sure you have Node.js installed on your computer, then use the following JSON config:
"Lucid Software": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.lucid.app/mcp"]
}
Authenticate with an API key
The Lucid MCP server uses OAuth by default, which requires a user to approve access the first time an AI tool connects. For autonomous processes that run without a person available to grant that approval, you can authenticate using an API key instead. To set up authentication with an API key, follow these steps:
- Generate an API key in the Lucid developer portal.
- Configure your MCP client to use the API key for authentication.
- The MCP client will authenticate using the permissions granted to that key automatically, with no login or approval prompt required at runtime.
For admins: Enable or disable use of the MCP server for your account
Admins on Team and Enterprise accounts can control whether or not to give users on their account access to the Lucid MCP server.
To restrict or permit access to the Lucid MCP server on your account:
- In your Lucid account, select Admin from the left-side panel.
- Click Security in the left-side menu.
- Select Feature controls from the menu to the left.
- Under “MCP access”, use the toggle next to "Allow users to connect”.
- Click Enable MCP or Disable MCP in the modal that appears.
Available actions with the Lucid MCP server
Once the Lucid MCP server has been set up, you can use it to complete various actions in Lucid by entering a prompt into your AI tool. As we add more use cases to the Lucid MCP server, you may need to re-authenticate with your AI tool in order for the new functionality to work.
The following use cases are currently supported:
| Functionality | Example |
| Search, fetch, and summarize content | |
| Search Lucid documents for specific content. | “Show me all Lucid documents that talk about the website redesign project.” |
| Fetch and summarize document details and content. | “Find the 'Q4 Website Redesign Workflow' document in Lucid, and give me a summary of action items.” |
| Fetch an image. | “Find the ‘Product Mockups’ document in Lucid and fetch the original source image attached to the ‘Feature A Screenshot’ shape.” |
| Retrieve document metadata. | “Can you check the metadata details on the Onboarding Process document? I need to know the document owner and when it was last modified." |
| Generate and edit content | |
| Create a diagram with prompting. | "Create a diagram in Lucid that maps out a user authentication flow.” |
| Create an org chart with a CSV file or text prompt that includes employee information. | "Use the attached CSV file to create an org chart in Lucid.” |
| Generate a UML sequence diagram from PlantUML markup. | “Create a UML sequence diagram in Lucid using the following PlantUML syntax.” |
| Generate a data-backed entity relationship diagram. | “Create a data-backed ERD in Lucid from this current database schema, keeping all tables, primary/foreign keys, and relationships intact." |
| Edit, add, or delete shapes in a document. | “In my Lucid IT Escalation Process document, update all decision blocks to a red fill with bold white text.” |
| Add synced Jira Cards to a document. | “Create Jira cards in my Lucid Sprint Planning board from the issues in my Jira Product Team 8 space.” |
| Generate, add items to, and edit Dynamic Tables. | “Generate a Dynamic Table in my Lucid brainstorming doc and map MCP-254 & DEV-333 Jira issues by assignee and status." |
| Share documents and collaborate | |
| Create a shareable link for a Lucid document. | "Create a shareable link with view-only permissions for my 'FY26 Q3 Product Roadmap' document in Lucid." |
| Share a document with specific collaborators using their email address. | "Share my 'Q1 Marketing Campaign Flowchart' document in Lucid with jsol@email.com. Add them with full Edit permissions." |
| Pull and respond to comments. | “Respond to Jill's comment on the flowchart about the updated schema.” |
| Manage content | |
| Move, create, rename folders. | “Change the name of my ‘IT Processes folder’ to ‘IT & Security processes.’” |
| Move and rename documents. | “Move my ‘March Sprint Review document’ to my ‘Q1 Sprint Reviews’ folder.” |
| Export a document as a PNG. | “Export of my ‘Project Timeline’ document in Lucid as a PNG file.” |
| Send feedback | |
| Send feedback about the MCP to Lucid’s team. | “Request an export diagram feature in Lucid’s MCP server.” |
Tip: If you have additional MCP servers set up in your AI tool, consider pairing them with the Lucid MCP server. For example you could use your AI tool to send a shareable link via email or add it to Confluence.
FAQ
How does the Lucid MCP server work?
The Lucid MCP server is a remote service available at https://mcp.lucid.app/mcp. It uses the streamable HTTP transport protocol, Client ID Metadata Document (CIMD), and Dynamic Client Registration (DCR) to securely manage client access. Authentication is handled via OAuth 2.0, allowing Lucid users to authorize the MCP server to integrate with their AI tools. During setup, users complete two distinct authorization steps:
- Server authentication: Verifies and registers the Lucid MCP server as a trusted service.
- Permission scope approval: Grants the MCP server access to user documents, data, and account operations within Lucid products.
Both authentication and scope approval are required before the Lucid MCP server can interact with a user’s account or data.
Can the Lucid MCP server fetch information from Process Accelerator repositories?
The Lucid MCP server can access information in Process Accelerator repositories, but it is not limited to repository documents. However, the Lucid repositories MCP server limits the search tools to only search repositories and fetch repository documents. For more information, check out this Help Center article.
Can Enterprise admins restrict access to specific AI clients?
Granting access to the Lucid MCP server allows users to connect to any AI client. If an account needs to restrict access to specific AI tools, you will need to disable the MCP at the account level.
What info can the Lucid MCP server access?
The Lucid MCP server can access any Lucid document you have permissions to access within your account, including titles, content, comments, and metadata. It cannot access documents owned or created by users outside your account.
How is my data used by the Lucid MCP server?
The Lucid MCP server acts as a pass-through and does not retain document content, user prompts, or queries. Your credentials are never shared outside your Lucid account. Usage of the Lucid MCP server is subject to the negotiated services agreement between the parties or Lucid’s standard Terms of Service available at https://lucid.co/tos.
What types of diagrams can the Lucid MCP server create?
The Lucid MCP server can generate any diagram type supported by Lucid, such as flowcharts, org charts, sequence diagrams, and entity relationship diagrams.
While the server can automatically build a diagram from your data (for example, turning a list of employees into an org chart), it creates a static version only. It cannot create data-linked diagrams that automatically update when your source data changes.
How does the Lucid MCP server differ from standard text-to-AI connections?
The MCP server uses a document-processing format to translate complex diagrams and text into a structure designed for LLMs. This ensures that when you ask for a summary, the AI understands the hierarchy and relationships within your document better than standard text-to-AI connections.
Resources
To learn more about this feature, explore the additional resources below. These resources are available in English only.
Community post
Introducing the Lucid Model Context Protocol (MCP) server
External resources
To learn more about MCP servers, check out this external documentation:
Give feedback on this article
Have feedback about this article? Tell us about your experience here.