The MCP Server lets AI assistants or AI agents such as ChatGPT, Microsoft Copilot, or Claude securely access your Meisterplan data and work with your portfolio and project data directly from your AI application.
Background: What Is an MCP Server?
The Meisterplan MCP Server (Model Context Protocol) is a standardized interface that lets AI agents securely access Meisterplan data, without having to export and manually transfer it to your AI agent.
Similar to the REST API, which makes Meisterplan data available to other applications, the MCP Server makes Meisterplan data available specifically to AI agents. When you ask a question, the AI agent automatically knows which Meisterplan data it needs.
The quality of the answers depends on the AI model you use. More capable models interact more effectively with the MCP Server and deliver more precise results.
Required User Rights
Which data you can retrieve via the MCP Server depends on the rights of the user account used to establish the connection. The MCP Server respects all field-level permissions of that user account.
To activate the MCP Server for a user group, navigate to Manage > User Groups > Views & Areas > AI Functionality and enable the Access MCP Server right. You can enable or disable access per user group.
What Our MCP Server Can Do
With our MCP Server, you can receive answers to portfolio and project questions without switching between Meisterplan and your AI agent, as well as feed your Meisterplan data into other workflows and reports.
You can currently retrieve the following Meisterplan data via the MCP Server, provided you have at least read-only rights:
- Projects with project details (e.g. Status, Goals including configured colors, Rank)
- Project KPIs (e.g. Total Costs, Total Effort, Total Capex, Total Opex, Total Benefits, Net Value)
- Scenarios
If a request includes data you do not have access to, the AI agent will return a partial answer along with a hint that some data was not accessible.
Use Cases
The following examples show how you can use the MCP Server in your day-to-day work:
Keeping Track of Critical Projects
Your portfolio contains dozens of projects and you want to quickly know which ones are critical and why, without opening each project individually.
Ask your AI agent:
| List all projects with the status Critical and explain why they might be critical. |
The AI agent identifies the affected projects and derives possible reasons from the associated project fields and KPIs.
Using Similar Projects for Planning
You are planning a new project and want to benefit from the experience of similar projects, but don't have time to search the portfolio manually.
Ask your AI agent:
| I want to create a new project X. Select three similar projects from the portfolio and create an overview of their key project fields and values. |
The AI agent finds comparable projects and compiles the relevant key figures so you can make realistic assumptions for your new plan.
Preparing for Meetings
You have a status meeting tomorrow and want to be up to date in a few minutes instead of having to tediously gather information from different views.
Ask your AI agent:
| I have a status meeting on project XY tomorrow. Summarize the most important key figures and current information for me. |
The AI agent compiles an overview of status, schedule, financial key figures, and relevant project fields, so you go into the meeting prepared.
Note on Costs:
AI agents typically charge for the amount of data processed per token. For large portfolios with many projects and custom fields, individual requests can consume a significant number of tokens. We recommend narrowing your questions to relevant projects or fields.
Getting Started
To use the MCP Server, you need an API token for the MCP Server from Meisterplan and an AI agent that supports MCP connections.
How to Connect Your AI Agent to the MCP Server
Make sure your user group has the Access MCP Server right and that you have created an API token. To create an API token for the MCP Server, navigate to My Profile > Manage API Tokens and click Add API Token. Select the type MCP Server Token and copy the token.
Then connect your AI agent to the MCP Server:
- Open the settings of your AI agent.
- Navigate to the section where you can set up an MCP Server connection.
- Enter the following MCP Server URL. Your URL will vary based on if your Meisterplan is hosted in the EU or the US:
EU: https://mcp.eu.meisterplan.com/mcp
US: https://mcp.us.meisterplan.com/mcp - Enter the following as the header for the API token: Authorization
- Grant the MCP server access by entering your API token for the MCP server. Use the format Bearer + space + <API token>
(e.g. Bearer abc123xyz).
Which User Account Is Used
Your AI agent operates with the rights of the user account that created the API token. There are two ways to connect:
- Each user connects individually. Each user creates their own MCP Server token and connects their AI agent with it. They only see data they have at least read-only rights for.
- The Meisterplan administration sets up a central AI agent. The administration creates an MCP Server token via a dedicated user account and connects a shared agent with it. All users of that agent see the data that the dedicated account has at least read-only rights for.
For central setups, we recommend creating a dedicated user account that is used exclusively for the MCP Server. This ensures that all users of a shared AI agent see exactly the data they are supposed to see, regardless of their own rights in Meisterplan.
Create this account under Manage > Users and add it to a user group whose rights match exactly what all users of the central agent should be able to see.
For answers to common questions about MCP Server, data processing and security, see the article Q&A: Meisterplan AI.