Your financial data now lives wherever your AI does. Abacum MCP lets you securely chat with your live models, scenarios, and actuals from your favorite AI assistant — no exports, no copy-paste.

✨ What's new

• Ask questions, get live answers. Query your P&L, run variance analysis, or prep for a board call — all from Claude or ChatGPT, using your real Abacum data.
• Local + Cloud in one conversation. Drag a PDF contract into your AI chat and ask: "Does this fit within my Q4 Marketing budget?" The AI reads your file and checks it against live Abacum data simultaneously.
• Secure by design. OAuth authentication, user-level permissions, and Super Admin activation control. The AI only sees what you can see in Abacum.

⚙️ How to set up

1. A Super Admin enables the MCP server in Company Settings → Connections & API.
2. Open your AI assistant (Claude or ChatGPT), go to Connectors and select Abacum when prompted.
3. Start asking questions.

⚠️ Good to know

• Only Super Admins can activate the MCP server. Once active, all Admins can connect.
  • If your plan does not include a "Super Admin" account, please contact your CS manager.
• Member-role users are not supported in this release.
• Your financial data is sent to the AI provider you connect to. Consult your security team before enabling.

📚 Learn more in the Abacum Academy

We’ve introduced three new formulas in Dataset Transformations to help you clean, standardize, and reuse your data more efficiently:

🧩 Clean JSON or list data in one step

From [{"first_name":"Mark","last_name":"Roberts"}] to Mark

You can now extract specific values from JSON objects or lists stored in a column. No complex workarounds, string manipulation, or external preprocessing required.

👉 Learn more about how to use EXTRACT_FROM_OBJECT

🔤 Convert text to upper or lower case

From mark roberts to MARK ROBERTS

Quickly convert any text field to uppercase or lowercase. Perfect for cleaning IDs, aligning formats across systems, and ensuring consistent comparisons and VLOOKUPs across your datasets.

👉 Learn more about how to use UPPER and LOWER

We’re improving the new Input Tables block to make it even more powerful and flexible.

Here’s what’s new:

• Use formulas that reference other cells: Reduce manual typing, avoid mistakes, and create more dynamic plans by building calculations based on values already in the table.
• Filter your Input Table: Navigate large tables faster and more efficiently by focusing on the data that matters. Apply filters directly within the Input Table in your Space using its dimension items.
• Edit dimension items: Adjust how values are allocated by editing the dimension items directly in the Input Table.

Want to dive deeper?
Check out the full guides and videos in our Academy:

• Formulas in Quick Calculations
• Input Table Filters
• Edit Dimension Items

With these updates, Input Tables keep getting smarter, helping finance teams and budget owners save time, reduce mistakes, and enjoy a more intuitive planning workflow.

✨ What’s new

We’ve upgraded our Amazon S3 integration to support IAM Role-based authentication. This provides a more robust connection that simplifies the setup process while meeting the highest security standards.

⚙️ How it works

While we still fully support Access Keys for those who prefer them, IAM Roles are now our officially recommended approach.

Instead of using a permanent "password," your AWS account establishes a trust relationship with Abacum:

• Enhanced security: Abacum uses temporary, short-lived credentials that expire automatically.
• Smart handshake: A unique External ID ensures that only your Abacum environment can access your specific S3 bucket.
• Minimal maintenance: No more worrying about rotating or expiring Access Keys.

You can choose your preferred method the next time you set up or update your connection. You can learn more about this on Abacum Academy: 👉 Amazon S3 Bucket Integration.

You can now delete multiple tables and charts at once to keep your workspace efficient and organized.

✨ What’s New

• Multi-select. Use the new checkboxes to select the items you wish to delete.
• Smart safety checks. We'll automatically warn you if a table you are deleting is being used in a Space, so you never break a report by accident.

Head to your Tables and charts manager to start your spring clean! Visit the Abacum Academy to learn more. 

Make sure your data is dynamic with our latest release, Inline Metrics, allowing you to embed live, auto-updating financial values directly into your written analysis.

✨ What’s new

• Live data narratives. Your executive summaries and monthly reports now stay 100% accurate. When your data updates, your sentences update with it.
• Variance at a glance. Don't just show a number—show the story. Embed variance percentages and comparisons directly in your text (e.g., $1.2M (-5% vs Budget)).
• Unified workspace. While metrics are the star of the show, we’ve also made it easier to navigate to other Abacum resources.

⚙️ How it works

• @ Metrics. Type @ to search for any variable and drop its live value right where you’re typing.
• Smart formatting. Just like KPI cards, you can customize the timeframe and comparison of your inline metrics to fit your narrative.
• Enhanced mentions. We've expanded our @ menu! Beyond teammates, you can now tag and link to any platform resource—Spaces, Datasets, and more—to keep everything connected.

Inline mentions are now available for all organisations. Learn more in the Abacum Academy.

The Input Table is a new planning block that lets you manage manual inputs directly inside Spaces, making updates faster, more intuitive, and far more flexible.

Here’s what you can do with it:

• Edit inputs without leaving the Space: No more pop-up panels. Update values inline while keeping actuals and other versions visible for clearer planning.
• Control timeframes for each version: Set them as fixed or allow them to update automatically as new actuals come in.
• Adjust and save multiple variables at once: Update all inputs in a single table, with performance improvements that make large edits faster and smoother.
• ➕ Improvements you’ve been waiting for: Hide irrelevant columns, show/hide rows that already have actuals, manage all input types in one place, and more.

How to get started:

1. Go to your Space
2. Type / to open the Space blocks menu
3. Select Input Table to start adding and editing your inputs

Want to dive deeper? Check out the full guide in our Academy.

With this release (and more improvements coming soon), Spaces now support a more complete, flexible planning workflow for both finance teams and budget owners.

We've completely rebuilt our AI assistant from the ground up. The new agent thinks autonomously, handles complex multi-step questions, and can now answer the "why" behind your numbers.

✨ What's new?

• Autonomous reasoning – The agent now understands your question and intelligently selects the right tools to answer it. Ask multiple things in one sentence, and it handles them seamlessly.
• Real-time thinking visibility – Watch the agent's reasoning process as it works through your question, step by step. No more guessing what's happening behind the scenes.
• Smarter response formatting – Simple questions get simple answers. The agent now returns values as text when appropriate, and only generates tables for complex breakdowns.
• Dimension splits – Ask "Revenue by Country" or "OPEX by Department" and get instant breakdowns by any dimension in your model.
• Main contributors analysis – Ask questions like "Why was OPEX so high in February?" and the agent identifies the top drivers across your dimensions automatically.
• Flexible time periods – Split and compare data by month, quarter, or year. No longer limited to totals.
• Refreshed UI – A cleaner interface aligned with Abacum Intelligence branding.

⚙️ How does it work?

Simply open the AI assistant and ask your question naturally. The agent will:

1. Analyze what you're asking
2. Select the appropriate tools (visible in the thinking panel)
3. Execute multi-step queries if needed
4. Return results in the most useful format

For dimension-based queries (splits or contributor analysis), use the exact dimension name from your model for best results.

Example queries to try:

• "What was revenue in January 2025?"
• "Show me gross margin by region for Q1"
• "What were the main contributors to OPEX in March?"
• "Compare Q4 revenue to Q3 by month"

⚠️ Good to know

Clear the conversation to ensure the Agent uses the new framework

Composition vs. causation – The agent can break down what makes up a number (e.g. which departments contributed to OPEX), but does not yet compare to prior periods to explain why a number changed. True variance analysis is on our roadmap.

Dimension names – For dimension-based queries (splits or contributor analysis), use the exact dimension name from your model for best results. Fuzzy matching improvements are coming soon.

🔜 Coming soon

We're continuing to enhance the agent with additional table features (prior period comparisons, dimension filtering) and chart generation.

📚 Learn more

✨ What’s new?

• Advanced customization. Design your reports exactly how you want them with precision resizing and new multi-column layouts that support up to four blocks in parallel.
• Look and feel. Our new text editor supports more formatting options and background colors, merging the best of text and callouts to tell the story behind the numbers.
• Intuitive UX. We’ve replaced typing commands with ‘+’ buttons located next to your blocks, making it easier than ever to add content exactly where you need it.
• Smoother experience. Enjoy a more stable viewing experience for large tables and an intuitive drag-and-drop interface.
• Visit the academy to learn more.

We are rolling this feature out in phases to ensure a smooth transition. If it is not yet visible in your environment, it will be arriving very soon. If you would like to start exploring the new functionalities sooner, please reach out to your Customer Success Manager.