Tracing Allocations with an MCP-Connected AI Agent

Once you’ve connected an AI agent to your workspace over the Model Context Protocol (MCP), you can ask it — in plain language — to trace cost through your allocation steps. You don’t run a report or write SQL: you ask a question, and the agent calls PlaidCloud’s allocation-tracing tools to find the model, explain a change, walk the chain, and answer what-if questions.

This works from any MCP-connected client — a chat agent (Claude Desktop, ChatGPT) or a coding agent (Claude Code, Cursor) — since they all reach the same tools over the MCP server.

Note

These tools read your allocation configuration and results — they don’t change anything. You can ask freely; nothing is written back to the project.

Prerequisites

• A project containing allocation steps (allocation_split, allocation_rules, or allocation_dim).
• An AI agent connected to your workspace over MCP — see Getting Started with AI Coding Agents.

What You Can Ask

Ask the agent …	What it does	Tool behind it
”What allocation models are in this project?”	Lists each model, its stages, and the result tables it produces	allocation_model_find
”How is cost_line_rev calculated?”	Shows the cost pool being split, the driver it is split by, and the target table	allocation_describe
”Why did cost_line_rev change from 2025 to 2026?”	Compares the two periods and attributes the change to the pool size versus the driver mix, with the top contributing accounts	allocation_root_cause
”What feeds cost_line_rev?”	Walks the upstream chain — drivers, source pools, and imports	allocation_lineage
”Where is revenue_by_line used as a driver?”	Lists every allocation that splits by that table	allocation_driver_usage
”What happens if US revenue rises by $1M?”	Estimates the downstream impact on each affected result table	allocation_forward_impact

Worked Example

A finance analyst notices a revenue-driven cost line has fallen year on year and asks one question. The agent answers it end to end, calling several allocation tools behind the scenes.

You ask: Our revenue-based cost allocation (cost_line_rev) looks down in 2026 versus 2025. What happened, what is it built from, and what would a +$1M US revenue swing do?

The agent replies:

What it is. cost_line_rev is the revenue-driven stage of your Activity-Based Costing (ABC) model. It takes a cost pool (group_amount, limited to a set of P&L accounts) and splits it by revenue from revenue_by_line, weighted within each entity, year, and month.

Why it dropped (US, 2025 → 2026). US-allocated cost fell from $7.12M to $2.99M — a $4.13M drop (−58.0%). This is not a mix shift: the US share of the pool held steady at about 23% in both years. The driver is the total cost pool shrinking, concentrated in a few accounts:

Account	2025	2026	Change
700000	$2.58M	$1.09M	−$1.49M
701000	$1.85M	$0.77M	−$1.08M
610000	$1.71M	$0.72M	−$0.99M
670000	$0.68M	$0.29M	−$0.39M
702000	$0.30M	$0.13M	−$0.18M

Those five accounts explain essentially all of the move.

What feeds it. cost_line_rev is built from revenue_by_line (the split driver) and gl_pool_entity (the cost pool).

Heads-up — that driver is shared. revenue_by_line also drives cost_line_cs and cost_line_admin, so a revenue restatement ripples into all three.

Your +$1M US scenario. A $1M US revenue increase could shift allocated cost by up to $1M in each of cost_line_rev, cost_line_cs, and cost_line_admin — three affected results, each an independent upper bound rather than a shared total.

The analyst gets a complete answer — the size of the change, the accounts behind it, the lineage, and the blast radius of a what-if — without opening a single table.

Good to Know

Filtered allocations get a clean, whole-pool answer

When an allocation’s source rows are restricted (for example to a set of P&L accounts), the agent applies that filter automatically and still gives a clean, whole-pool attribution — you don’t need to add anything.

Dimension allocations

For an allocation driven by a dimension hierarchy — for example, splitting a cost centre across a reporting structure — the agent reports the correct totals and per-member movements but flags the precise cause as partial. Attributing it needs point-in-time hierarchy history, which is a later release.

Cascaded allocations need a slice

When one allocation feeds another — a cascade — a project-wide “why” would mix the wrong rows, so the agent asks you to scope the question to a slice (a specific region, product, or cost centre) and then explains it.

What-if estimates are upper bounds

“What happens if …” answers are upper bounds — they assume the full change flows to each target, so the per-table figures are worst-case envelopes, not additive totals. Use them to size the blast radius, not as a precise forecast.

Tips

• Refer to tables by their name (cost_line_rev) or their id — both work.
• For a change question, name the periods to compare (for example 2025 versus 2026) and, where useful, a breakdown dimension such as account or entity.
• Start broad (“what allocation models are in this project?”) and drill in; the agent keeps the thread, so follow-up questions build on the same model.

Related

• Getting Started with AI Coding Agents — connect an agent to your workspace over MCP
• Why Allocations Are Useful — allocation concepts
• Troubleshooting — connection and authentication issues